# Papers

Name | Authors | Short description | Book title | Year | Actions |
---|---|---|---|---|---|

Active Pointillistic Pattern Search |
Yifei Ma and Dougal J. Sutherland and Roman Garnett and Jeff Schneider | Active Pointillistic Pattern Search, paper and code | 2015 | show | |

Fast Function to Function Regression |
Junier B. Oliva, Willie Neiswanger, Barnabás Póczos, Eric Xing, Hy Trac, Shirley Ho, Jeff Schneider | AISTATS 2015 | 2015 | show | |

Active Search and Bandits on Graphs Using Sigma-Optimality |
Yifei Ma and Tzu-Kuo Huang and Jeff Schneider | A second paper in the series of Sigma-optimality, a mysterious idea which seems crazy at first but actually provokes thoughts. | UAI | 2015 | show |

Generalization Bounds for Transfer Learning under Model Shift | UAI | 2015 | show | ||

On the Error of Random Fourier Features | Uncertainty in Artificial Intelligence | 2015 | show | ||

A Machine Learning Approach for Dynamical Mass Measurements of Galaxy Clusters |
Michelle Ntampaka, Hy Trac, Dougal J. Sutherland, Nicholas Battaglia, Barnabás Póczos, and Jeff Schneider | 2015 | show | ||

Dynamical Mass Measurements of Contaminated Galaxy Clusters Using Machine Learning |
Michelle Ntampaka, Hy Trac, Dougal J. Sutherland, Sebastian Fromenteau, Barnabás Póczos, and Jeff Schneider. | 2015 | show | ||

Active Area Search via Bayesian Quadrature |
Yifei Ma and Roman Garnett and Jeff Schneider | Gateway to "AAS via BQ". Paper and Code | 2014 | show | |

Fast Distribution To Real Regression |
Junier Oliva, Willie Neiswanger, Barnabas Poczos, Jeff Schneider, Eric Xing | AISTATS 2014 | 2014 | show | |

FuSSO: Functional Shrinkage and Selection Operator |
Junier Oliva, Barnabas Poczos, Timothy Verstynen, Aarti Singh, Jeff Schneider, Fang-Cheng Yeh, Wen-Yih Tseng | AISTATS 2014 | 2014 | show | |

Active Transfer Learning under Model Shift | ICML | 2014 | show | ||

Learning from Point Sets with Observational Bias | Uncertainty in Artificial Intelligence (UAI) | 2014 | show | ||

Flexible Transfer Learning under Support and Model Shift | transfer learning with flexible transformation on both features and labels | NIPS | 2014 | show | |

Thesis proposal | 2014 | show | |||

Distribution to Distribution Regression | ICML 2013 | 2013 | show | ||

Spectral Learning of Hidden Markov Models from Dynamic and Static Data | Proceedings of the 30th International Conference on Machine Learning | 2013 | show | ||

Active Search on Graphs | a soft-label model and the impact criterion for active search on large graph datasets | KDD 2013 | 2013 | show | |

Active Learning and Search on Low-Rank Matrices | ACM SIGKDD | 2013 | show | ||

Sigma-Optimality in Active Learning on Gaussian Random Fields |
Yifei Ma and Roman Garnett and Jeff Schneider | A new heuristic proposed. Algorithmic bounds discovered. | NIPS | 2013 | show |

Efficient Learining on Point Sets | IEEE International Conference on Data Mining | 2013 | show | ||

Learning Hidden Markov Models from Non-sequence Data via Tensor Decomposition | Advances in Neural Information Processing Systems | 2013 | show | ||

Separation Theorem for Independent Subspace Analysis and its Consequences | Review on different generalizations of independent subspace analysis and the ISA separation principle. | Pattern Recognition | 2012 | show | |

Kernels on Sample Sets via Nonparametric Divergence Estimates |
Dougal J. Sutherland, Liang Xiong, Barnabás Póczos, Jeff Schneider | Kernel algorithms on distributions | Technical Report | 2012 | show |

Collaborative Filtering via Group-Structured Dictionary Learning | Application of structured dictionary learning for collaborative filtering | LVA-ICA 2012 | 2012 | show | |

Nonparametric Estimation of Conditional Information and Divergences | nonparametric conditional mutual information estimator | AISTATS 2012 | 2012 | show | |

Nonparametric Kernel Estimators for Image Classification |
Barnabas Poczos, Liang Xiong, Dougal J. Sutherland, Jeff Schneider | nonparametric kernel estimation for image classification | CVPR 2012 | 2012 | show |

Copula-based Kernel Dependency Measures | Copula-based Kernel Dependency Measures | ICML 2012 | 2012 | show | |

Bayesian Optimal Active Search and Surveying |
Roman Garnett, Yamuna Krishnamurthy, Xuehan Xiong, Jeff Schneider, Richard Mann | Proceredings of the 29th Annual International Conference on Machine Learning (ICML 2012) | 2012 | show | |

Maximum Margin Output Coding | Maximum Margin Output Coding | ICML | 2012 | show | |

Learning Bi-clustered Vector Autoregressive Models | ECML | 2012 | show | ||

An Impact Criterion for Active Graph Search | proposed impact criterion for active graph search | NIPS workshop on Bayesian Optimization and Decision Making | 2012 | show | |

A Composite Likelihood View for Multi-Label Classification | A Composite Likelihood View for Multi-Label Classification | AISTATS 2012 | 2012 | show | |

On the Estimation of alpha-Divergences | A nonparametric Renyi and Tsallis divergence estimator | AISTATS 2011 | 2011 | show | |

Hierarchical Probabilistic Models for Group Anomaly Detection |
Liang Xiong, Barnabas Poczos, Jeff Schneider, Andrew Connolly, Jake VanderPlas | Multinomial genre model for group anomaly detection | AISTATS 2011 | 2011 | show |

Online Group-Structured Dictionary Learning | Online dictionary learning method which enables overlapping group structures with non-convex sparsity-inducing regularization and handles the partially observable case | CVPR 2011 | 2011 | show | |

Multi-label Output Codes using Canonical Correlation Analysis | Multi-label Output Codes using Canonical Correlation Analysis | AISTATS 2011 | 2011 | show | |

Nonparametric Divergence Estimation for Machine Learning on Distributions | Learning Workshop (Snowbird) poster | 2011 | show | ||

Nonparametric Independent Process Analysis | EUSIPCO 2011 | 2011 | show | ||

Nonparametric Divergence Estimators for Independent Subspace Analysis | Nonparametric Divergence Estimators for Independent Subspace Analysis | EUSIPCO 2011 | 2011 | show | |

Online Dictionary Learning with Group Structure Inducing Norms | ICML 2011 workshop paper on online dictionary learning with group structure inducing norms | ICML-2011 workshop on "Structured Sparsity: Learning and Inference" | 2011 | show | |

Nonparametric divergence estimation with applications to machine learning on distributions | Divergence estimatiors with applications to clustering, classification, low-dimensional embedding, outlier detection. | UAI 2011 | 2011 | show | |

Learning Dynamic Models from Non-sequenced Data | Learning workshop (Snowbird) poster | 2011 | show | ||

Direct Robust Matrix Factorization |
Liang Xiong, Xi Chen, Jeff Schneider | IEEE International Conference on Data Mining | 2011 | show | |

Group Anomaly Detection using Flexible Genre Models | flexible genre models | NIPS | 2011 | show | |

Robust Nonparametric Copula Based Dependence Estimators |
Barnabas Poczos, Sergey Krishner, David Pal, Csaba Szepesvari, Jeff Schneider | Review on copula based dependence estimators | Copulas in machine learning. Nips 2011 Workshop | 2011 | show |

Learning Auto-regressive Models from Sequence and Non-sequence Data | Combining sequence and non-sequence data to improve dynamic model learning | NIPS 2011 | 2011 | show | |

Bayesian Optimal Active Search on Graphs |
Roman Garnett, Yamuna Krishnamurthy, Donghan Wang, Jeff Schneider, Richard Mann | Proceedings of the Ninth Annual Workshop on Mining and Learning with graphs (MLG 2011), at KDD 2011. | 2011 | show | |

Temporal Collaborative Filtering with Bayesian Probabilistic Tensor Factorization |
Liang Xiong, Xi Chen, Tzu-Kuo Huang, Jeff Schneider, Jaime G. Carbonell | Bayesian probabilistic tensor factorization | Proceedings of SIAM Data Mining | 2010 | show |

Learning Compressible Models | Learning Compressible Models | In Proceedings of SIAM Data Mining (SDM) Conference | 2010 | show | |

Learning Nonlinear Dynamic Models from Non-sequenced Data |
Tzu-Kuo Huang, Le Song, Jeff Schneider | Proceedings of the 13th International Conference on Artificial Intelligence and Statistics (AISTATS) 2010 | 2010 | show | |

Projection Penalties: Dimension Reduction without Loss | Projection Penalties for Using Dimension Reduction without Loss | ICML 2010 | 2010 | show | |

Multi-task Active Learning with Output Constraints | A multi-task active learning framework with task outputs coupled by constraints | AAAI 2010 | 2010 | show | |

Fast Nearest-neighbor Search in Disk-resident Graphs | 2010 | show | |||

Learning Multiple Tasks with a Sparse Matrix-Normal Penalty | NIPS 2010 | 2010 | show | ||

Estimation of Renyi Entropy and Mutual Information Based on Generalized Nearest-Neighbor Graphs |
David Pal, Barnabas Poczos, Csaba Szepesvari | A nonparametric method for entropy and mutual information estimation. We prove consistency and provide convergence rates. | NIPS 2010 | 2010 | show |

T-Cube Web Interface as a tool for detecting disease outbreaks in real-time: A pilot in India and Sri Lanka |
Nuwan Waidyanatha, Chamindu Sampath, Artur Dubrawski, Maheshkumar Sabhnani, Lujie Chen | T-Cube Web Interface for detecting disease outbreaks | RIVF 2010 | 2010 | show |

Automated Detection of Data Entry Errors in a Real Time Surveillance System |
Lujie Chen, Artur Dubrawski, Nuwan Waidyanatha, Chamindu Weerasinghe | Error detection in real time biosurveillance | Advances in Disease Surveillance | 2010 | show |

Challenges of Introducing Disease Surveillance Technology in Developing Countries: Experiences from India and Sri Lanka |
Chamindu Weerasinghe, Nuwan Waidyanatha, Artur Dubrawski, Michael Baysek | 2010 | show | ||

Fast Dynamic Reranking in Large Graphs | International World Wide Web Conference | 2009 | show | ||

Learning Linear Dynamical Systems without Sequence Information | ICML 2009: Proceedings of the 26th International Conference on Machine Learning | 2009 | show | ||

Trade-offs between Agility and Reliability of Predictions in Dynamic Social Networks Used to Model Risk of Microbial Contamination of Food | Best paper award, ASONAM 2009 | 2009 International Conference on Advances in Social Network Analysis and Mining ASONAM 2009 | 2009 | show | |

Evolution of a Useful Autonomous System |
Artur Dubrawski, Henry Thorne | Proceedings of the 7th International Workshop on Robot Motion and Control | 2009 | show | |

T-Cube Web Interface in Support of Real-Time Bio-surveillance Program |
Artur Dubrawski, Maheshkumar Sabhnani, Michael Knight, Michael Baysek, Daniel Neill, Saswati Ray, Anna Michalska, Nuwan Waidyanatha | Proceedings of the International Conference on Information and Communication Technologies and Development ICTD 2009 | 2009 | show | |

Smart PCA | Smart PCA algorithm to incorporate domain knowledge into dimension reduction | IJCAI 2009 | 2009 | show | |

T-Cube Web Interface for Real-time Biosurveillance in Sri Lanka |
Maheshkumar Sabhnani, Artur Dubrawski, Nuwan Waidyanatha | Advances in Disease Surveillance | 2009 | show | |

Discovering Possible Linkages between Food-borne Illness and the Food Supply Using an Interactive Analysis Tool |
Artur Dubrawski, Lujie Chen, Maheshkumar Sabhnani, Paula J. Fedorka-Cray,
| Advances in Disease Surveillance | 2009 | show | |

Compact Spatial Joins |
Brent Bryan, Frederick Eberhardt, Christos Faloutsos | ICDE | 2008 | show | |

Actively Learning Level-Sets of Composite Functions | ICML 2008: Proceedings of the 25th International Conference on Machine Learning | 2008 | show | ||

Fast Incremental Proximity Search in Large Graphs |
Purnamrita Sarkar, Andrew W. Moore, Amit Prakash | Slightly revised from the ICML camera-ready version | Proceedings of the 25th International Conference on Machine Learning | 2008 | show |

Anomaly Pattern Detection in Categorical Datasets | Proceedings of 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2008) | 2008 | show | ||

Learning the Semantic Correlation: An Alternative Way to Gain from Unlabeled Text | A semi-supervised learning algorithm on text | NIPS | 2008 | show | |

Dynamic Network Model for Predicting Occurrences of Salmonella at Food Facilities | BioSecure 2008 | 2008 | show | ||

Efficiently Computing Minimax Expected-Size Confidence Regions |
Brent Bryan, H. Brendan McMahan, Chad M. Schafer, Jeff Schneider | ICML 2007: Proceedings of the 24th International Conference on Machine Learning | 2007 | show | |

Mapping the Cosmological Confidence Ball Surface |
Brent Bryan, Jeff Schneider, Christopher J. Miller, Robert C. Nichol, Christopher Genovese, Larry Wasserman | 2007 | show | ||

A Tractable Approach to Finding Closest Truncated-commute-time Neighbors in Large Graphs | The 23rd Conference on Uncertainty in Artificial Intelligence(UAI) | 2007 | show | ||

A Latent Space Approach to Dynamic Embedding of Co-occurrence Data | Proceedings of the Eleventh International Conference on Artificial Intelligence and Statistics (AI-STATS) | 2007 | show | ||

Detecting Anomalous Records in Categorical Datasets | Proc. of the thirteenth ACM SIGKDD international conference on Knowledge discovery and data mining | 2007 | show | ||

A Study into Detection of Bio-Events in Multiple Streams of Surveillance Data | Intelligence and Security Informatics: Biosurveillance | 2007 | show | ||

A Constraint Generation Approach to Learning Stable Linear Dynamical Systems |
Byron Boots | Advances in Neural Information Processing Systems | 2007 | show | |

Fast State Discovery for HMM Model Selection and Learning | Proceedings of the Eleventh International Conference on Artificial Intelligence and Statistics (AI-STATS) | 2007 | show | ||

Actively Learning Specific Function Properties with Applications to Statistical Inference | 2007 | show | |||

Applying Outbreak Detection Algorithms to Prognostics |
Artur Dubrawski, Michael Baysek, Shannon Mikus, Charles McDaniel, Bradley Mowry, Laurel Moyer, John Ostlund, Norman Sondheimer, Timothy Stewart | AAAI Fall Symposium on Artificial Intelligence in Prognostics | 2007 | show | |

T-Cube as an Enabling Technology in Surveillance Applications |
Artur Dubrawski, Maheshkumar Sabhnani, Saswati Ray, Josep Roure, Michael Baysek | Advances in Disease Surveillance | 2007 | show | |

Dependency Trees in Sub-linear Time and Bounded Memory | Efficient learning of dependency trees for huge datasets. | 2006 | show | ||

Monitoring Food Safety by Detecting Patterns in Consumer Complaints |
Artur Dubrawski, Kimberly Elenberg, Andrew Moore, Maheshkumar Sabhnani | Proceedings of the National Conference on Artificial Intelligence AAAI/IAAI 2006 | 2006 | show | |

Autonomous Visualization | European Conference on Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD 2006) | 2006 | show | ||

Sequential Update of ADtrees | ICML | 2006 | show | ||

Disease Outbreak Detection using Discriminative Random Field |
Kaustav Das, Robin Sabhnani, Eric Xing | 2006 | show | ||

Detecting Significant Multidimensional Spatial Clusters | Applying the fast multidimensional spatial scan statistic to detect clusters in epidemiological and brain imaging data. | Advances in Neural Information Processing Systems 17 | 2005 | show | |

Efficiently Identifying Close Track/Observation Pairs in Continuous Timed Data |
Jeremy Kubica, Andrew Moore, Andrew Connolly, Robert Jedicke | Proc. SPIE Signal and Data Processing of Small Targets | 2005 | show | |

Fast Inference and Learning in Large-State-Space HMMs | Proceedings of the 22nd International Conference on Machine Learning | 2005 | show | ||

Making Logistic Regression A Core Data Mining Tool: A Practical Investigation of Accuracy, Speed, and Simplicity | Regularized logistic regression can be fast, accurate, and simple. This paper includes the most important findings of my thesis, and a few new details. | 2005 | show | ||

Alias Detection in Link Data Sets | Combining string similarity with contextual similarity when searching for aliases using active learning. | Proceedings of the International Conference on Intelligence Analysis | 2005 | show | |

Algorithms for rapid outbreak detection: a research synthesis | 2005 | show | |||

A Multiple Tree Algorithm for the Efficient Association of Asteroid Observations |
Jeremy Kubica, Andrew Moore, Andrew Connolly, Robert Jedicke | The Eleventh ACM SIGKDD International Conference on Knowledge Discovery and Data Mining | 2005 | show | |

Making Logistic Regression A Core Data Mining Tool With TR-IRLS | This short paper is the easiest, fastest way to learn about Truncated Regularized Iteratively Re-weighted Least Squares (TR-IRLS), my algorithm for fast, parameter-free logistic regression. TR-IRLS can also be used for any generalized linear model. This | Proceedings of the 5th International Conference on Data Mining Machine Learning | 2005 | show | |

Finding Optimal Bayesian Networks by Dynamic Programming | Learning the optimal Bayes net structure | 2005 | show | ||

Person Identification in Webcam Images: An Application of Semi-Supervised Learning |
| 2005 | show | ||

Bayesian Detection of Router Configuration Anomalies | ACM SIGCOMM Workshop on Mining Network Data (MineNet-05) | 2005 | show | ||

Anomalous Spatial Cluster Detection | A general and powerful framework for spatial cluster detection. | Proceedings of the KDD 2005 Workshop on Data Mining Methods for Anomaly Detection | 2005 | show | |

Detecting Anomalous Patterns in Pharmacy Retail Data | A bio-surveillance system to collect disease outbreak feedback from public health officials | Proceedings of the KDD 2005 Workshop on Data Mining Methods for Anomaly Detection | 2005 | show | |

Dynamic Social Network Analysis using Latent Space Models | 2005 | show | |||

Learning Predictive Models from Small Sets of Dirty Data | 2005 | show | |||

Efficient Analytics for Effective Monitoring of Biomedical Security |
Robin Sabhnani, Daniel B. Neill, Andrew W. Moore, Artur W. Dubrawski, Weng-Keen Wong | 2005 | show | ||

Variable KD-Tree Algorithms for Spatial Pattern Search and Discovery |
Jeremy Kubica, Joseph Masiero, Andrew Moore, Robert Jedicke, Andrew Connolly | Advances in Neural Information Processing Systems | 2005 | show | |

Active Learning For Identifying Function Threshold Boundaries |
Brent Bryan, Jeff Schneider, Robert C. Nichol, Christopher J. Miller, Christopher R. Genovese, Larry Wasserman | 2005 | show | ||

Bayes Net Graphs to Understand Coauthorship Networks | 2005 | show | |||

A Bayesian spatial scan statistic |
Daniel Neill, Andrew Moore, Gregory Cooper | A new Bayesian method for spatial cluster detection | Advances in Neural Information Processing Systems | 2005 | show |

A Bayesian scan statistic for spatial cluster detection |
Daniel Neill, Andrew Moore, Gregory Cooper | A new Bayesian method for cluster detection | Proceedings of the National Syndromic Surveillance Conference | 2005 | show |

Tractable Learning of Large Bayes Net Structures from Sparse Data | in this paper we propose an algorithm that allows to learn a Bayes Net structure from sparse data (e.g., power-law distributed) with over 100,000 variables. we also report time and performance accuracy when applied to several very large datasets | ICML | 2004 | show | |

Alias Detection in Link Data Sets | An active learning approach to deciding whether two names correspond to the same entity, combining string similarity information and context similarity. | 2004 | show | ||

Rapid Detection of Significant Spatial Clusters | A new spatial scan algorith that searches over arbitrary rectangles in addition to squares. | 2004 | show | ||

The IOC algorithm: Efficient Many-Class Non-parametric Classification for High-Dimensional Data | Performing k-nearest-neghbor classifications on multi-class problems without actually finding the k-nearest neighbors. | Proceedings of the conference on Knowledge Discovery in Databases (KDD) | 2004 | show | |

Semantic based Biomedical Image Indexing and Retrieval |
Yanxi Liu, N Lazar, W Rothfus, Frank Dellaert, Andrew Moore, Jeff Schneider, Takeo Kanade | Volumetric pathological neuroimage retrieval under the framework of classification-driven feature selection. | Trends and Advances in Content-Based Image and Video Retrieval | 2004 | show |

Active Learning for Anomaly and Rare-Category Detection | How to use active learning in a real-life scenario. | Advances in Neural Information Processing Systems 18 | 2004 | show | |

Fast Nonlinear Regression via Eigenimages Applied to Galactic Morphology |
Brigham Anderson, Andrew Moore, Andrew Connolly, Robert Nichol | Determining the shapes of millions of galaxies. | 2004 | show | |

High-Dimensional Probabilistic Classification for Drug Discovery | Discriminative probabilistic classifiers have been used successfully on large life-sciences datasets, but high dimensionalities have prohibited the use of nonparametric class probability estimation. This paper explores a method (SLAMDUNK) which addresses | Proceedings of the Computational Statistics | 2004 | show | |

Logistic Regression for Data Mining and High-Dimensional Classification | We document several approached to logistic regression parameter estimation, and detail the most promising implementation for high-dimensinal classification. | 2004 | show | ||

An Investigation of Practical Approximate Nearest Neighbor Algorithms | How to use variations on classic exact data structures for nearest neighbor, if you want to get faster answers and are prepared to accept approximation? | 2004 | show | ||

Belief State Approaches to Signaling Alarms in Surveillance Systems | KDD 2004 Proceedings | 2004 | show | ||

Fast Robust Logistic Regression for Large Sparse Datasets with Binary Outputs | Logistic regression can provide faster, better results than SVM for life-sciences datasets with hundreds of thousands of attributes. | Artificial Intelligence and Statistics | 2003 | show | |

A Comparison of Statistical and Machine Learning Algorithms on the Task of Link Completion |
Anna Goldenberg, Jeremy Kubica, Paul Komarek, Andrew Moore, Jeff Schneider | This paper examines the task of link completion, relative algorithm performance, and what this can tell us about the structure of the data. | KDD Workshop on Link Analysis for Detecting Complex Behavior | 2003 | show |

Covariant Policy Search | A simple algorithm leads to very fast, covariant policy search. | Proceedings of the International Joint Conference on Artificial Intelligence | 2003 | show | |

Policy Search by Dynamic Programming | Dynamic programming techniques can make direct policy search computationally and sample efficient. | Proceedings of Neural Information Processing Systems | 2003 | show | |

Probabilistic Noise Identification and Data Cleaning | We examine the use of explicit noise and corruption models to aid in the task of noise identification and data cleaning. | The Third IEEE International Conference on Data Mining | 2003 | show | |

cGraph: A Fast Graph-Based Method for Link Analysis and Queries | This paper is an extended version of the 2003 ICML conference paper. | Proceedings of the 2003 IJCAI Text-Mining & Link-Analysis Workshop | 2003 | show | |

Finding Underlying Connections: A Fast Graph-Based Method for Link Analysis and Collaboration Queries | CGraph is an algorithm to quickly learn a graph-based model of the underlying connections of a set of entities given link data. | Proceedings of the International Conference on Machine Learning | 2003 | show | |

Tractable Group Detection on Large Link Data Sets | We present the k-groups algorithm, an improvement of the GDA algorithm that includes significant computational advantages. The k-groups algorithm allows tractable group detection on large data sets. | The Third IEEE International Conference on Data Mining | 2003 | show | |

Optimal Reinsertion: A new search operator for accelerated and more accurate Bayesian network structure learning | Very aggressive but computationally efficient search steps for Bayes net learning. | Proceedings of the 20th International Conference on Machine Learning (ICML '03) | 2003 | show | |

What's Strange About Recent Events |
Weng-Keen Wong, Andrew Moore, Gregory Cooper, Michael Wagner | A shorter paper on WSARE that was submitted to the Journal of Urban Health | 2003 | show | |

Empirical Bayes Screening for Link Analysis | An algorithm for discovering top N strange co-occurences of size 2,3,4, etc Uses ideas of frequent sets, but stratifies them according to a statistically justified hierarchical bayes model, using empirical bayes to find the parameters | Workshop on Text Analysis and Link Detection, IJCAI | 2003 | show | |

Bayesian Network Anomaly Pattern Detection for Disease Outbreaks |
Weng-Keen Wong, Andrew Moore, Gregory Cooper, Michael Wagner | Handles temporal trends in data by replacing the baseline of WSARE 2.0 with a baseline generated by a Bayesian network. | Proceedings of the Twentieth International Conference on Machine Learning | 2003 | show |

A Fast Multi-Resolution Method for Detection of Significant Spatial Overdensities | Scaling up the classical Kulldorff scan statistic. | 2003 | show | ||

Efficient Exact k-NN and Nonparametric Classification in High Dimensions | Can we do non-approximate k-NN classification without actually finding the k-NN? | Proceedings of Neural Information Processing Systems | 2003 | show | |

Rapid Evaluation of Multiple Density Models | A way to quickly evaluate and compare multiple nonparametric density estimates. | Artificial Iintelligence and Statistics | 2003 | show | |

A Fast Multi-Resolution Method for Detection of Significant Spatial Disease Clusters | Rapid detection of disease clusters using a fast spatial scan statistic algorithm. | Advances in Neural Information Processing Systems 16 | 2003 | show | |

Variable Resolution Discretization in Optimal Control | A short paper on choosing the right resolution in a tessalation of state space. | 2002 | show | ||

Rule-based Anomaly Pattern Detection for Detecting Disease Outbreaks |
Weng-Keen Wong, Andrew Moore, Gregory Cooper, Michael Wagner | Answering the question: "What's Strange About Recent Events?" | Proceedings of the 18th National Conference on Artificial Intelligence | 2002 | show |

Summary of Biosurveillance-relevant statistical and data mining technologies | A brief informal survey of some techniques that have been used for Biosurveillance. | 2002 | show | ||

Stochastic Link and Group Detection | This paper introduces the GDA algorithm. We use noisy link data (n-tuples of entities) to learn underlying groupings of entities. | Proceedings of the Eighteenth National Conference on Artificial Intelligence | 2002 | show | |

Efficient Algorithms for Non-Parametric Clustering with Clutter | Finding and counting the high density regions in spatial data. | Proceedings of the 34th Interface Symposium | 2002 | show | |

Interpolating Conditional Density Trees | Very fast non-parametric Bayesian Network nodes | Conference on Uncertainty in Artificial Intelligence | 2002 | show | |

Using Tarjan's Red Rule for Fast Dependency Tree Construction | Very fast growth of dependency trees. | 2002 | show | ||

Real-valued All-Dimensions search: Low-overhead rapid searching over subsets of attributes | Searching over large numbers of contingency tables quickly | Proceedings of the 18th Conference on Uncertainty in Artificial Intelligence | 2002 | show | |

Active Learning in Discrete Input Spaces | Using modified Gittins indices to decide which datapoint to actively label next whilst being rewarded for each new label. | Proceedings of the 34th Interface Symposium | 2002 | show | |

Direct Policy Search using Paired Statistical Tests | If you're going to choose the best policy by roll-outs, how can statistical tests and "racing" help? | Proceedings of the 18th International Conference on Machine Learning | 2001 | show | |

Solving Uncertain Markov Decision Problems | Finding good policies in uncertain models | 2001 | show | ||

Mixtures of Rectangles: Interpretable Soft Clustering | A mixture model that is easily readable by humans. | Proceedings of the 18th International Conference on Machine Learning | 2001 | show | |

Repairing Faulty Mixture Models using Density Estimation | Intelligent automatic selection of new mixture model components | International Conference on Machine Learning | 2001 | show | |

N-Body Problems in Statistical Learning | A way to use multiple trees simultaneously to solve a large class of statistical problems efficiently. | Advances in Neural Information Processing Systems | 2001 | show | |

Classification-Driven Pathological Neuroimage Retrieval Using Statistical Asymmetry Measures |
Yanxi Liu, Frank Dellaert, W Rothfus, Andrew Moore, Jeff Schneider, Takeo Kanade | Using machine learning to detect abnormalities in neuro-imaging output. | Proceedings of the 2001 Medical Imaging Computing and Computer Assisted Intervention Conference (MICCAI '01) | 2001 | show |

Autonomous Helicopter Control using Reinforcement Learning Policy Search Methods | We consider the difficult control problem of learing to fly an autonomous helicopter using limited observational data of its dynamics. To that end, we develop policy search techiques that perform well on average with respect to dynamic consistent with our | Proceedings of the International Conference on Robotics and Automation | 2001 | show | |

Reinforcement Learning for Cooperating and Communicating Reactive Agents in Electrical Power Grids | One approach to distributed reinforcement learning | Balancing Reactivity and Social Deliberation in Multi-Agent Systems | 2001 | show | |

A Nonparametric Approach to Noisy and Costly Optimization | Optimizing a noisy process in a possibly discontinuous or non-euclidian space. | International Conference on Machine Learning | 2000 | show | |

Condensed Representations for computationally tractable data mining of massive sky surveys |
Andrew Moore, Robert Nichol, Larry Wasserman, Andrew Connolly | 2000 | show | ||

A Dynamic Adaptation of AD-trees for Efficient Machine Learning on Large Data Sets | Fast implementation of on-demand AD-trees for scores of high-arity attributes and millions of rows. | Proceedings of the 17th International Conference on Machine Learning | 2000 | show | |

The Anchors Hierarchy: Using the Triangle Inequality to Survive High-Dimensional Data | Using Ball-trees allows cached sufficient statistics-based accelerations even in high dimensions. The Anchors approach quickly optimizes the Ball-tree structure for this purpose. | Proceedings of the Twelfth Conference on Uncertainty in Artificial Intelligence | 2000 | show | |

X-means: Extending K-means with Efficient Estimation of the Number of Clusters | Extension to popular K-means, where the number of clusters K is also estimated. | Proceedings of the Seventeenth International Conference on Machine Learning | 2000 | show | |

Learning Filaments | A generative model and efficient algorithm for identifying noisy networks of points in k-dimensional space | Proceedings of the International Conference on Machine Learning | 2000 | show | |

Mixnets: Learning Bayesian Networks with mixtures of discrete and continuous attributes | Bayes Nets with Mixture Models in the nodes | Proceedings of the Twelfth Conference on Uncertainty in Artificial Intelligence | 2000 | show | |

Bayesian Networks for Lossless Dataset Compression | Practical ways to compress large tabular datasets | Proceedings of the Fifth International Conference on Knowledge Discovery in Databases | 1999 | show | |

Efficient Multi-Object Dynamic Query Histograms | Using Multiresolution kdtrees to accelerate visualization algorithms | Proceedings of the IEEE Symposium on Information Visualization | 1999 | show | |

Influence and Variance of a Markov Chain: Application to adaptive discretization in optimal control | You're using variable resolution splines to approximate a value function. Where is most profitable to increasing the resolution? | Conference on Decision and Control (CDC99) | 1999 | show | |

Variable Resolution discretizations for high-accuracy solutions of optimal control problems | Proceedings of the International Joint Conference on Artificial Intelligence, Stockholm | 1999 | show | ||

Distributed Value Functions |
Jeff Schneider, Weng-Keen Wong, Andrew Moore, Martin Riedmiller | Distributed Reinforcement learning for applications such a power grids | Proceedings of the 16th International Conference on Machine Learning | 1999 | show |

Accelerating Exact k-means Algorithms with Geometric Reasoning | Using cached counts and a different kind of search operator during k-means updates, with no approximation | Proceedings of the Fifth International Conference on Knowledge Discovery in Databases | 1999 | show | |

Very Fast EM-based Mixture Model Clustering Using Multiresolution KD-trees | Using kdtrees with centroids in the nodes can allow accurate EM updates in time sublinear in the number of records | Advances in Neural Information Processing Systems | 1999 | show | |

Accelerating Exact k-means Algorithms with Geometric Reasoning (Extended version) | This is an extended version of the KDD99 paper. | 1999 | show | ||

Multi-Value-Functions: Efficient Automatic Action Hierarchies for Multiple Goal MDPs | An efficient procedure to approximately compute all policies for all possible goal states. | Proceedings of the International Joint Conference on Artificial Intelligence, Stockholm | 1999 | show | |

Applying online search techniques to Continuous-State reinforcement learning | Using a specialized version of A-star to boost the performance of approximate value functions | Proceedings of the Fifteenth National Conference on Artificial Intelligence | 1998 | show | |

AD-trees for Fast Counting and for Fast Learning of Association Rules | Using AD-trees to learn conjunctive rules via beam search. | Knowledge Discovery from Databases Conference | 1998 | show | |

Learning Evaluation Functions for Global Optimization and Boolean Satisfiability | Proceedings of the Fifteenth National Conference on Artificial Intelligence | 1998 | show | ||

Cached Sufficient Statistics for Efficient Machine Learning with Large Datasets | Introduces AD-trees: a new way to implicitly pre-cache the answers to all possible counting queries for a dataset. | 1998 | show | ||

Q2: Memory-based active learning for optimizing noisy continuous functions | Maximizing a very noisy function in k-dimensional space with few samples | Proceedings of the Fifteenth International Conference of Machine Learning | 1998 | show | |

Value Function Based Production Scheduling | Production scheduling in which we account for a probability distribution on future jobs by means of kernel-based value function approximation | Proceedings of the 15th International Conference on Machine Learning | 1998 | show | |

Simulation-based optimization of a stochastic product coating problem using hash-table cacheing of costs | 1997 | show | |||

Multidimensional Triangulation and Interpolation for Reinforcement Learning | Neural Information Processing Systems 9, | 1997 | show | ||

A tutorial on using the Vizier memory-based learning system | A tutorial on using the Windows Vizier software for fast locally weighted and k-NN style classification and regression. | 1997 | show | ||

Locally Weighted Learning for Control | How can kernel methods and locally weighted regression help robots learn to control themselves? | 1997 | show | ||

Using Prediction to Improve Combinatorial Optimization Search | Automatically improving combinatorial search by reinforcement-learning-style analysis of earlier runs | American Association for Artificial Intelligence C | 1997 | show | |

Exploiting Model Uncertainty Estimates for Safe Dynamic Control Learning | Advances in Neural Information Processing Systems 9, | 1997 | show | ||

Locally Weighted Learning | Survey of the use of kernel functions in kernel regression, locally weighted regression and related function approximators. | 1997 | show | ||

Efficient Locally Weighted Polynomial Regression Predictions | Using Multiresolution KD-trees with cached first and second moments in the nodes | Proceedings of the Fourteenth International Conference on Machine Learning | 1997 | show | |

Memory based Stochastic Optimization for Validation and Tuning of Function Approximators | Conference on AI and Statistics | 1997 | show | ||

The Racing Algorithm: Model Selection for Lazy Learners | A detailed analysis and study of Racing. | Artificial Intelligence Review | 1997 | show | |

Algorithms for Approximating Optimal Value Functions in Acyclic Domains | Using "Rollouts" to make value-function-based RL more practical | Machine Learning: Proceedings of the Thirteenth International Conference | 1996 | show | |

Reinforcement Learning: A Survey | Surveys MDPs, TD, Q-learning and many other Reinforcement Learning staples. | 1996 | show | ||

Memory-based Stochastic Optimization | Using locally weighted regression to model response surfaces and to choose the next experiment | Neural Information Processing Systems 8 | 1996 | show | |

Proceedings of the Workshop on Value Function Approximation, Machine Learning Conference 1995. | Short talks from a workshop about value function approximation | 1995 | show | ||

Variable Resolution Reinforcement Learning | Briefly surveys a number of approaches to making Bellman updates faster | Proceedings of the Eighth Yale Workshop on Adaptiv | 1995 | show | |

An Empirical Investigation of Brute Force to choose Features, Smoothers and Function Approximators | What happens when you use very intense cross-validation? | Computational Learning Theory and Natural Learning | 1995 | show | |

Generalization in Reinforcement Learning: Safely Approximating the Value Function | An introduction to the ways that naive application of function approximation of value functions can fail. | Neural Information Processing Systems 7 | 1995 | show | |

Learning Automated Product Recommendations Without Observable Features: An Initial Investigation | 1995 | show | |||

The Parti-game Algorithm for Variable Resolution Reinforcement Learning in Multidimensional State-spaces | Automatic variable resolution discretization of a multidimensional state space during searches for shortest paths | 1995 | show | ||

Multiresolution Instance-based Learning | Multiresolution Kd-trees with cached statistics for accelerating kernel regression | Proceedings of the Twelfth International Joint Conference on Artificial Intellingence | 1995 | show | |

Task-level Training Signals for Learning Controllers | A new learning algorithm and an example on the inverted pendulum task | Proceedings of the IEEE Symposium on Intelligent Control | 1994 | show | |

A short tutorial note on computing information gain from counts | A simple 2-page tutorial. | 1994 | show | ||

Hoeffding Races: Accelerating Model Selection Search for Classification and Function Approximation | Perform many cross-validation operations in a round-robin fashion, pruning likely non-winners early. | Advances in Neural Information Processing Systems | 1994 | show | |

Efficient Algorithms for Minimizing Cross Validation Error | Proceedings of the 11th International Confonference on Machine Learning | 1994 | show | ||

High Dimension Action Spaces in Robot Skill Learning | Proceedings of the Twelfth National Conference on Artificial Intelligence | 1994 | show | ||

The Parti-game Algorithm for Variable Resolution Reinforcement Learning in Multidimensional State-spaces | A short introduction to an efficient learning-shortest-paths algorithm. | Advances in Neural Information Processing Systems | 1994 | show | |

Prioritized Sweeping: Reinforcement Learning with Less Data and Less Real Time | As estimates of rewards and transition probabilites improve during learning, how can we efficiently allow the value function to keep up? | 1993 | show | ||

Memory-based Reinforcement Learning: Efficient Computation with Prioritized Sweeping | Using a priority queue to schedule the most useful value function updates | Advances in Neural Information Processing Systems | 1992 | show | |

Fast, Robust Adaptive Control by Learning only Forward Models | A real robot pool player achieves high accuracy by learning in a forward direction. | Advances in Neural Information Processing Systems | 1992 | show | |

Knowledge of Knowledge and Intelligent Experimentation for Learning Control | Proceedings of the 1991 Seattle International Joint Conference on Neural Networks | 1991 | show | ||

Variable Resolution Dynamic Programming: Efficiently Learning Action Maps in Multivariate Real-valued State-spaces | Machine Learning: Proceedings of the Eighth International Conference | 1991 | show | ||

A tutorial on kd-trees | A description of Bentley et al's classic nearest neighbor algorithm | University of Cambridge Computer Laboratory Technical Report No. 209 | 1991 | show | |

Acquisition of Dynamic Control Knowledge for a Robotic Manipulator | Proceedings of the 7th International Conference on Machine Learning | 1990 | show | ||

Efficient Memory-based Learning for Robot Control | Using KD-trees, nearest neighbor and active learning. | 1990 | show | ||

Experiments in Adaptive State Space Robotics | Using a nearest neighbor classifier to design control experiments | Proceedings of the 7th AISB Conference, Brighton | 1989 | show | |

Learning Robotic Control: PhD. Thesis Proposal | Thesis Proposal | 1988 | show | ||

Yifei | show |