Andrew W. Moore

The IOC algorithm: Efficient Many-Class Non-parametric (2004)

This paper describes Stage, a learning approach to automatically improving search performance on optimization problems. Stage learns an evaluation function which predicts the outcome of a local...

Ting Liu, Ke Yang, Andrew W. Moore

This paper is about a variant of k nearest neighbor classification on large many-class high dimensional datasets.

Rapid Detection of Significant Spatial Clusters (2004)

A Fast Multi-Resolution Method for Detection of Significant Spatial Disease Clusters (2004)

Given an NN grid of squares, where each square has a count c i j and an underlying population p i j , our goal is to find the rectangular region with the highest density, and to calculate its...

An Intoductory Tutorial on Kd-Trees (2004)

Given an NN grid of squares, where each square has a count and an underlying population, our goal is to find the square region with the highest density, and to calculate its significance by...

An Implementation-Based Comparison of Measurement-Based Admission Control Algorithms (2004)

This paper considers the expected number of hyperrectangles corresponding to leaf nodes which will provably need to be searched. Such hyperrectangles intersect the volume enclosed byahypersphere...

Hoeffding Races: Accelerating Model (2004)

In this paper we present an implementation-based comparison of Measurement-based Admission Control algorithms. Through the use of a special purpose environment, a performance and behaviour comparison...

Oded Maron, Andrew W. Moore

Selecting a good model of a set of input points by cross validation is a computationally intensive process, especially if the number of possible models or the number of training points is high....

New Algorithms for Efficient High-Dimensional Nonparametric (2004)

Ting Liu, Andrew W. Moore, Alexander Gray, Pack Kaelbling

This paper is about non-approximate acceleration of high dimensional nonparametric operations such as k nearest neighbor classifiers and the prediction phase of Support Vector Machine classifiers.

Efficient Exact k-NN and Nonparametric (2004)

Ting Liu, Andrew W. Moore, Alexander Gray

This paper is about non-approximate acceleration of high dimensional nonparametric operations such as k nearest neighbor classifiers and the prediction phase of Support Vector Machine classifiers. We...

Generalization in Reinforcement Learning: Safely Approximating the Value Function Justin A. Boyan and Andrew W. Moore (2004)

New Algorithms for Efficient High Dimensional (2004)

To appear in: G. Tesauro, D. S. Touretzky and T. K. Leen, eds., Advances in Neural Information Processing Systems 7, MIT Press, Cambridge MA, 1995. A straightforward approach to the curse of...

Ting Liu, Andrew W. Moore, Alexander Gray

This paper is about non-approximate acceleration of high dimensional nonparametric operations such as k nearest neighbor classifiers and the prediction phase of Support Vector Machine classifiers. We...

Very Fast Outlier Detection in Large Multidimensional Data Sets (2004)

Amitabh Chaudhary, Er S. Szalay, Andrew W. Moore

Outliers are objects that do not comply with the general behavior of the data. Applications such as exploration in science databases need fast interactive tools for outlier detection in data sets...

Efficient Exact k-NN and Nonparametric (2004)

Ting Liu, Andrew W. Moore, Alexander Gray

This paper is about non-approximate acceleration of high dimensional nonparametric operations such as k nearest neighbor classifiers and the prediction phase of Support Vector Machine classifiers. We...

A Fast Multi-Resolution Method for Detection of Significant Spatial Disease Clusters (2004)

Multi-Tree Methods for Statistics on Very Large Datasets in Astronomy (2004)

Given an NN grid of squares, where each square has a count and an underlying population, our goal is to find the square region with the highest density, and to calculate its significance by...

Gray, Alexander G., Moore, Andrew W., Nichol, Robert C., Connolly, Andrew J., Genovese, Christopher, Wasserman, Larry

Many fundamental statistical methods have become critical tools for scientific data analysis yet do not scale tractably to modern large datasets. This paper will describe very recent algorithms based...

A Fast Multi-Resolution Method for Detection of (2003)

Policy Search using Paired Comparisons (2003)

Given an N N grid of squares, where each square s ij has a count c ij and an underlying population p ij , our goal is to nd the square region S with the highest density, and to calculate the signi...

Hampshire Gu, Andrew W. Moore, E. Brodley, Andrea Danyluk

Direct policy search is a practical way to solve reinforcement learning (RL) problems involving continuous state and action spaces. The goal becomes finding policy parameters that maximize a noisy...

Journal of Machine Learning Research 3 (2002) 921-950 Submitted 12/01; Published 12/02 Policy Search using Paired Comparisons (2003)

Hampshire Gu, Andrew W. Moore, E. Brodley, Andrea Danyluk

Direct policy search is a practical way to solve reinforcement learning (RL) problems involving continuous state and action spaces. The goal becomes finding policy parameters that maximize a noisy...

Art patronage and collecting, practice and curatorship : defining a region's cultural identity / (2003)

Moore, Andrew W.

Thesis (Ph.D.)--University of East Anglia, 2003.

Rapid Evaluation of Multiple Density Models (2002)

Fast Robust Logistic Regression for Large Sparse Datasets with Binary Outputs (2002)

When highly-accurate and/or assumptionfree density estimation is needed, nonparametric methods are often called upon - most notably the popular kernel density estimation (KDE) method. However, the...

Paul R. Komarek, Andrew W. Moore

Although popular and extremely well established in mainstream statistical data analysis, logistic regression is strangely absent in the field of data mining. There are two possible explanations of...

Network Monitoring with Nprobe (2002)

Andrew W. Moore, Rolf Neugebauer, James Hall, Ian Pratt

This paper presents an architecture for monitoring 10 Gbps networks, drawing on experience from a current 1 Gbps implementation. The architecture performs full line-rate capture and implements...

Very Fast Outlier Detection in Large Multidimensional Data Sets (2002)

Amitabh Chaudhary, Er S. Szalay, Andrew W. Moore

Outliers are objects that do not comply with the general behavior of the data. Applications such as exploration in science databases need fast interactive tools for outlier detection in data sets...

Repairing Faulty Mixture Models using Density Estimation (2001)

Peter Sand, Andrew W. Moore

Previous work in mixture model clustering has focused primarily on the issue of model selection. Model scoring functions (including penalized likelihood and Bayesian approxi- mations) can guide a...

`N-Body' Problems in Statistical Learning (2001)

The Anchors Hierarchy: Using the Triangle Inequality to Survive High Dimensional Data (2001)

We present efficient algorithms for all-point-pairs problems, or 'Nbody '-like problems, which are ubiquitous in statistical learning. We focus on six examples, including nearest-neighbor...

Non-Parametric Inference in Astrophysics (2001)

This paper is about metric data structures in high-dimensional or non-Euclidean space that permit cached sufficient statistics accelerations of learning algorithms.

Wasserman, Larry, Miller, Christopher J., Nichol, Robert C., Genovese, Chris, Jang, Woncheol, Connolly, Andrew J., ...

We discuss non-parametric density estimation and regression for astrophysics problems. In particular, we show how to compute non-parametric confidence intervals for the location and size of peaks of...

Direct Policy Search using Paired Statistical Tests (2001)

Andrew W Moore

Direct policy search is a practical way to solve reinforcement learning problems involving continuous state and action spaces. The goal becomes finding policy parameters that maximize a noisy...

Repairing Faulty Mixture Models using Density Estimation (2001)

Peter Sand, Andrew W. Moore

Previous work in mixture model clustering has focused primarily on the issue of model selection. Model scoring functions (including penalized likelihood and Bayesian approximations) can guide a...

Direct Policy Search using Paired Statistical Tests (2001)

Andrew W Moore

Direct policy search is a practical way to solve reinforcement learning problems involving continuous state and action spaces. The goal becomes finding policy parameters that maximize a noisy...

`N-Body' Problems in Statistical Learning (2001)

Learning Evaluation Functions to Improve Optimization by Local Search (2000)

We present efficient algorithms for all-point-pairs problems, or 'N-body'-like problems, which are ubiquitous in statistical learning. We focus on six examples, including nearest-neighbor...

Justin A. Boyan, Andrew W. Moore, Pack Kaelbling

This paper describes algorithms that learn to improve search performance on largescale optimization tasks. The main algorithm, Stage, works by learning an evaluation function that predicts the...

Remi Munos, Leemon C. Baird and Andrew W. Moore (2000)

Remi Munos, Leemon C. Baird, Andrew W. Moore

In this paper we investigate new approaches to dynamic-programming-based optimal control of continuous time-and-space systems. We use neural networks to approximate the solution to the...

A Nonparametric Approach to Noisy and Costly Optimization (2000)

Brigham S. Anderson, Andrew W. Moore

This paper describes Pairwise Bisection: a nonparametric approach to optimizing a noisy function with few function evaluations. The algorithm uses nonparametric reasoning about simple geometric...

`N-Body' Problems in Statistical Learning (2000)

The Anchors Hierarchy: Using the Triangle Inequality to Survive High Dimensional Data (2000)

We present very fast algorithms for a large class of statistical problems, which we call all-point-pairs problems, or 'N-body'-like problems. These are problems which abstractly require a comparison...

A Locally Weighted Learning Tutorial using Vizier 1.0 (2000)

This paper is about metric data structures in high-dimensional or non-Euclidean space that permit cached sufficient statistics accelerations of learning algorithms. It has recently been shown that...

Jeff Schneider, Andrew W. Moore

Contents 1 Introduction 3 1.1 The Vizier 1.0 User Interface : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 3 1.2 The data opportunity : : : : : : : : : : : : : : : : : : : :...

Learning Evaluation Functions for Global Optimization and Boolean Satisfiability (2000)

Q2: Memory-based active learning for optimizing noisy continuous functions (2000)

This paper describes STAGE, a learning approach to automatically improving search performance on optimization problems. STAGE learns an evaluation function which predicts the outcome of a local...

Andrew W. Moore, Jeff G. Schneider, Justin A. Boyan, Mary S. Lee

This paper introduces a new algorithm, Q2, for optimizing the expected output of a multi-input noisy continuous function. Q2 is designed to need only a few experiments, it avoids strong assumptions...

Learning Evaluation Functions to Improve Local Search (2000)

Justin A. Boyan and Andrew W. Moore (2000)

This paper describes Stage, a learning algorithm that automatically improves search performance on large-scale optimization problems. Stage learns an evaluation function that predicts the outcome of...

Value Function Based Production Scheduling (2000)

This paper describes Stage, a learning approach to automatically improving search performance on optimization problems. Stage learns an evaluation function which predicts the outcome of a local...

Jeff G. Schneider, Justin A. Boyan, Andrew W. Moore

Production scheduling, the problem of sequentially configuring a factory to meet forecasted demands, is a critical problem throughout the manufacturing industry. The requirement of maintaining...

Using Prediction to Improve Combinatorial Optimization Search (2000)

Q2: Memory-based active learning for optimizing noisy continuous functions (2000)

To appear in AISTATS-97 This paper describes a statistical approach to improving the performance of stochastic search algorithms for optimization. Given a search algorithm A, we learn to predict the...

Andrew W. Moore, Jeff G. Schneider, Justin A. Boyan, Mary S. Lee

This paper introduces a new algorithm, Q2, for optimizing the expected output of a multi-input noisy continuous function. Q2 is designed to need only a few experiments, it avoids strong assumptions...

Efficient Locally Weighted Polynomial Regression Predictions (2000)

Andrew W. Moore, Jeff Schneider, Kan Deng

Locally weighted polynomial regression (LWPR) is a popular instance-based algorithm for learning continuous non-linear mappings. For more than two or three inputs and for more than a few thousand...

The Parti-game Algorithm for Variable Resolution Reinforcement Learning in Multidimensional State-spaces (2000)

Andrew W. Moore, Christopher G. Atkeson

. Parti-game is a new algorithm for learning feasible trajectories to goal regions in high dimensional continuous state-spaces. In high dimensions it is essential that learning does not plan...

Layered Learning in Multi-Agent Systems (2000)

Peter Stone, Andrew W. Moore, Herbert A. Simon

Multi-agent systems in complex, real-time domains require agents to act effectively both autonomously and as part of a team. This dissertation addresses multi-agent systems consisting of teams of...

Reinforcement Learning: A Survey (1999)

Leslie Pack Kaelbling, Michael L. Littman, Andrew W. Moore

This paper surveys the field of reinforcement learning from a computer-science perspective. It is written to be accessible to researchers familiar with machine learning. Both the historical basis of...

Reinforcement Learning: A Survey (1999)

Leslie Pack Kaelbling, Michael L. Littman, Andrew W. Moore

This paper surveys the field of reinforcement learning from a computer-science perspective. It is written to be accessible to researchers familiar with machine learning. Both the historical basis of...

Value Function Based Production Scheduling (1999)

Jeff G. Schneider, Justin A. Boyan, Andrew W. Moore

Production scheduling, the problem of sequentially configuring a factory to meet forecasted demands, is a critical problem throughout the manufacturing industry. The requirement of maintaining...

Hoeffding Races: Accelerating Model Selection Search for Classification and Function Approximation (1999)

Oded Maron, Andrew W. Moore

Selecting a good model of a set of input points by cross validation is a computationally intensive process, especially if the number of possible models or the number of training points is high....

Efficient Algorithms for Minimizing Cross Validation Error (1999)

Andrew W. Moore, Mary S. Lee

Model selection is important in many areas of supervised learning. Given a dataset and a set of models for predicting with that dataset, we must choose the model which is expected to best predict...

Learning to Recognize Time Series: Combining ARMA models with Memory-based Learning (1999)

Kan Deng, Andrew W. Moore, Michael C. Nechyba

For a given time series observation sequence, we can estimate the parameters of the AutoRegression Moving Average (ARMA) model, thereby representing a potentially long time series by a limited...

On the Greediness of Feature Selection Algorithms (1999)

Kan Deng, Andrew W. Moore

: Based on our analysis and experiments using real-world datasets, we find that the greediness of forward feature selection algorithms does not severely corrupt the accuracy of function approximation...

Using Prediction to Improve Combinatorial Optimization Search (1999)

Generalization in Reinforcement Learning: Safely Approximating the Value Function (1999)

To appear in AISTATS-97 This paper describes a statistical approach to improving the performance of stochastic search algorithms for optimization. Given a search algorithm A, we learn to predict the...

Robust Value Function Approximation by Working Backwards (1999)

To appear in: G. Tesauro, D. S. Touretzky and T. K. Leen, eds., Advances in Neural Information Processing Systems 7, MIT Press, Cambridge MA, 1995. A straightforward approach to the curse of...

An Empirical Investigation of Brute Force to choose Features, Smoothers and Function Approximators (1999)

In this paper, we examine the intuition that TD() is meant to operate by approximating asynchronous value iteration. We note that on the important class of discrete acyclic stochastic tasks, value...

Andrew W. Moore, Daniel J. Hill, Michael P. Johnson

The generalization error of a function approximator, feature set or smoother can be estimated directly by the leave-one-out cross-validation error. For memory-based methods, this is computationally...

Prioritized Sweeping: Reinforcement Learning with Less Data and Less Real Time (1999)

Andrew W. Moore, Christopher G. Atkeson

We present a new algorithm, Prioritized Sweeping, for efficient prediction and control of stochastic Markov systems. Incremental learning methods such as Temporal Differencing and Qlearning have fast...

Locally Weighted Bayesian Regression (1999)

Learning Evaluation Functions for Large Acyclic Domains (1999)

hted regression query, if it is "close" to the query point it gets a weight of 1, and then as the distance to the query is increased the weight changes according to some non-increasing function....

Locally Weighted Learning (1999)

Some of the most successful recent applications of reinforcement learning have used neural networks and the TD() algorithm to learn evaluation functions. In this paper, we examine the intuition that...

Christopher G. Atkeson, Andrew W. Moore, Stefan Schaal

This paper surveys locally weighted learning, a form of lazy learning and memorybased learning, and focuses on locally weighted linear regression. The survey discusses distance functions, smoothing...

Memory-based Stochastic Optimization (1999)

Andrew W. Moore, Jeff Schneider

In this paper we introduce new algorithms for optimizing noisy plants in which each experiment is very expensive. The algorithms build a global non-linear model of the expected output at the same...

Reinforcement Learning: A Survey (1999)

Leslie Pack Kaelbling, Michael L. Littman, Andrew W. Moore

This paper surveys the field of reinforcement learning from a computer-science perspective. It is written to be accessible to researchers familiar with machine learning. Both the historical basis of...

An Intoductory Tutorial on Kd-Trees (1999)