Thomas G. Dietterich

Bio: Thomas G. Dietterich is an academic researcher from Oregon State University. The author has contributed to research in topics: Reinforcement learning & Markov decision process. The author has an hindex of 74, co-authored 279 publications receiving 51935 citations. Previous affiliations of Thomas G. Dietterich include University of Wyoming & Stanford University.

Gaussian Approximation of Collective Graphical Models

Abstract: The Collective Graphical Model (CGM) models a population of independent and identically distributed individuals when only collective statistics (i.e., counts of individuals) are observed. Exact inference in CGMs is intractable, and previous work has explored Markov Chain Monte Carlo (MCMC) and MAP approximations for learning and inference. This paper studies Gaussian approximations to the CGM. As the population grows large, we show that the CGM distribution converges to a multivariate Gaussian distribution (GCGM) that maintains the conditional independence properties of the original CGM. If the observations are exact marginals of the CGM or marginals that are corrupted by Gaussian noise, inference in the GCGM approximation can be computed efficiently in closed form. If the observations follow a different noise model (e.g., Poisson), then expectation propagation provides efficient and accurate approximate inference. The accuracy and speed of GCGM inference is compared to the MCMC and MAP methods on a simulated bird migration problem. The GCGM matches or exceeds the accuracy of the MAP method while being significantly faster.

Confidence Calibration for Domain Generalization under Covariate Shift

Abstract: Existing calibration algorithms address the problem of covariate shift via unsupervised domain adaptation. However, these methods suffer from the following limitations: 1) they require unlabeled data from the target domain, which may not be available at the stage of calibration in real-world applications and 2) their performances heavily depend on the disparity between the distributions of the source and target domains. To address these two limitations, we present novel calibration solutions via domain generalization which, to the best of our knowledge, are the first of their kind. Our core idea is to leverage multiple calibration domains to reduce the effective distribution disparity between the target and calibration domains for improved calibration transfer without needing any data from the target domain. We provide theoretical justification and empirical experimental results to demonstrate the effectiveness of our proposed algorithms. Compared against the state-of-the-art calibration methods designed for domain adaptation, we observe a decrease of 8.86 percentage points in expected calibration error, equivalently an increase of 35 percentage points in improvement ratio, for multi-class classification on the Office-Home dataset.

An efficient ATMS for equivalence relations

Abstract: We introduce a specialized ATMS for efficiently computing equivalence relations in multiple contexts. This specialized ATMS overcomes the problems with existing solutions to reasoning with equivalence relations. The most direct implementation of an equivalence relation in the ATMS—encoding the reflexive, transitive and symmetric rules in the consumer architecture— produces redundant equality derivations and requires Θ(n3) label update attempts (where n is the number of terms in an equivalence class). An alternative implementation is one that employs simple equivalence classes. However, this solution is unacceptable, since the number of classes grows exponentially with the number of distinct assumptions. The specialized ATMS presented here produces no redundant equality derivations, requires only Θ(n2) label update attempts, and is most efficient when there are many distinct assumptions. This is achieved by exploiting a special relationship that holds among the labels of the equality assertions because of transitivity. The standard dependency structure construction and traversal is replaced by a single pass over each label in a weaker kind of equivalence class. The specialized ATMS has been implemented as part of the logic programming language FORLOG.

Solving K-MDPs

Abstract: Markov Decision Processes (MDPs) are employed to model sequential decision-making problems under uncertainty Traditionally, algorithms to solve MDPs have focused on solving large state or action spaces With increasing applications of MDPs to human-operated domains such as conservation of biodiversity and health, developing easy-to-interpret solutions is of paramount importance to increase uptake of MDP policies Here, we define the problem of solving K-MDPs, ie, given an original MDP and a constraint on the number of states (K), generate a reduced state space MDP that minimizes the difference between the original optimal MDP value function and the reduced optimal K-MDP value function Building on existing non-transitive and transitive approximate state abstraction functions, we propose a family of three algorithms based on binary search with sub-optimality bounded polynomially in a precision parameter: ϕQ*eK-MDP-ILP, ϕQ*dK-MDP and ϕa*dK-MDP We compare these algorithms to a greedy algorithm (ϕQ*e Greedy K-MDP) and clustering approach (k-means++ K-MDP) On randomly generated MDPs and two computational sustainability MDPs, ϕa*dK-MDP outperformed all algorithms when it could find a feasible solution While numerous state abstraction problems have been proposed in the literature, this is the first time that the general problem of solving K-MDPs is suggested We hope that our work will generate future research aiming at increasing the interpretability of MDP policies in human-operated domains

Conformal Prediction Intervals for Markov Decision Process Trajectories

Abstract: Before delegating a task to an autonomous system, a human operator may want a guarantee about the behavior of the system. This paper extends previous work on conformal prediction for functional data and conformalized quantile regression to provide conformal prediction intervals over the future behavior of an autonomous system executing a fixed control policy on a Markov Decision Process (MDP). The prediction intervals are constructed by applying conformal corrections to prediction intervals computed by quantile regression. The resulting intervals guarantee that with probability 1 − δ the observed trajectory will lie inside the prediction interval, where the probability is computed with respect to the starting state distribution and the stochasticity of the MDP. The method is illustrated on MDPs for invasive species management and StarCraft2 battles.

Random Forests

Abstract: Random forests are a combination of tree predictors such that each tree depends on the values of a random vector sampled independently and with the same distribution for all trees in the forest. The generalization error for forests converges a.s. to a limit as the number of trees in the forest becomes large. The generalization error of a forest of tree classifiers depends on the strength of the individual trees in the forest and the correlation between them. Using a random selection of features to split each node yields error rates that compare favorably to Adaboost (Y. Freund & R. Schapire, Machine Learning: Proceedings of the Thirteenth International conference, aaa, 148–156), but are more robust with respect to noise. Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the splitting. Internal estimates are also used to measure variable importance. These ideas are also applicable to regression.

Gradient-based learning applied to document recognition

Abstract: Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradient based learning technique. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters, with minimal preprocessing. This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task. Convolutional neural networks, which are specifically designed to deal with the variability of 2D shapes, are shown to outperform all other techniques. Real-life document recognition systems are composed of multiple modules including field extraction, segmentation recognition, and language modeling. A new learning paradigm, called graph transformer networks (GTN), allows such multimodule systems to be trained globally using gradient-based methods so as to minimize an overall performance measure. Two systems for online handwriting recognition are described. Experiments demonstrate the advantage of global training, and the flexibility of graph transformer networks. A graph transformer network for reading a bank cheque is also described. It uses convolutional neural network character recognizers combined with global training techniques to provide record accuracy on business and personal cheques. It is deployed commercially and reads several million cheques per day.

Going deeper with convolutions

Abstract: We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

Deep Learning

Abstract: Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning. The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models. Deep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. A website offers supplementary material for both readers and instructors.

Reinforcement Learning: An Introduction

Abstract: Reinforcement learning, one of the most active research areas in artificial intelligence, is a computational approach to learning whereby an agent tries to maximize the total amount of reward it receives when interacting with a complex, uncertain environment. In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple account of the key ideas and algorithms of reinforcement learning. Their discussion ranges from the history of the field's intellectual foundations to the most recent developments and applications. The only necessary mathematical background is familiarity with elementary concepts of probability. The book is divided into three parts. Part I defines the reinforcement learning problem in terms of Markov decision processes. Part II provides basic solution methods: dynamic programming, Monte Carlo methods, and temporal-difference learning. Part III presents a unified view of the solution methods and incorporates artificial neural networks, eligibility traces, and planning; the two final chapters present case studies and consider the future of reinforcement learning.