Off-policy learning (OPL) often involves minimizing a risk estimator based on importance weighting to correct bias from the logging policy used to collect data. However, this method can produce an estimator with a high variance. A common solution is to regularize the importance weights and learn the policy by minimizing an estimator with penalties derived from generalization bounds specific to the estimator. This approach, known as pessimism, has gained recent attention but lacks a unified framework for analysis. To address this gap, we introduce a comprehensive PAC-Bayesian framework to examine pessimism with regularized importance weighting. We derive a tractable PAC-Bayesian generalization bound that universally applies to common importance weight regularizations, enabling their comparison within a single framework. Our empirical results challenge common understanding, demonstrating the effectiveness of standard IW regularization techniques.
Stochastic Gradient Descent (SGD) has become popular for solving large scale supervised machine learning optimization problems such as SVM, due to their strong theoretical guarantees. While the closely related Dual Coordinate Ascent (DCA) method has been implemented in various software packages, it has so far lacked good convergence analysis. This paper presents a new analysis of Stochastic Dual Coordinate Ascent (SDCA) showing that this class of methods enjoy strong theoretical guarantees that are comparable or better than SGD. This analysis justifies the effectiveness of SDCA for practical a…
Regularized regression problems are ubiquitous in statistical modeling, signal processing, and machine learning. Sparse regression in particular has been instrumental in scientific model discovery, including compressed sensing applications, variable selection, and high-dimensional analysis. We propose a broad framework for sparse relaxed regularized regression, called SR3. The key idea is to solve a relaxation of the regularized problem, which has three advantages over the state-of-the-art: (1) solutions of the relaxed problem are superior with respect to errors, false positives, and condition…
Model-based offline reinforcement learning (RL) aims to find highly rewarding policy, by leveraging a previously collected static dataset and a dynamics model. While the dynamics model learned through reuse of the static dataset, its generalization ability hopefully promotes policy learning if properly utilized. To that end, several works propose to quantify the uncertainty of predicted dynamics, and explicitly apply it to penalize reward. However, as the dynamics and the reward are intrinsically different factors in context of MDP, characterizing the impact of dynamics uncertainty through rew…
We propose a compressive classification framework for settings where the data dimensionality is significantly higher than the sample size. The proposed method, referred to as compressive regularized discriminant analysis (CRDA) is based on linear discriminant analysis and has the ability to select significant features by using joint-sparsity promoting hard thresholding in the discriminant rule. Since the number of features is larger than the sample size, the method also uses state-of-the-art regularized sample covariance matrix estimators. Several analysis examples on real data sets, including…
Sandia National Laboratories（桑迪亚国家实验室）；Xilinx Inc.（赛灵思公司）；Georgia Institute of Technology（佐治亚理工学院）
Bayesian optimization (BO) is an efficient and flexible global optimization framework that is applicable to a very wide range of engineering applications. To leverage the capability of the classical BO, many extensions, including multi-objective, multi-fidelity, parallelization, latent-variable model, have been proposed to improve the limitation of the classical BO framework. In this work, we propose a novel multi-objective (MO) extension, called srMO-BO-3GP, to solve the MO optimization problems in a sequential setting. Three different Gaussian processes (GPs) are stacked together, where each…
The regularized random forest (RRF) was recently proposed for feature selection by building only one ensemble. In RRF the features are evaluated on a part of the training data at each tree node. We derive an upper bound for the number of distinct Gini information gain values in a node, and show that many features can share the same information gain at a node with a small number of instances and a large number of features. Therefore, in a node with a small number of instances, RRF is likely to select a feature not strongly relevant. Here an enhanced RRF, referred to as the guided RRF (GRRF), is…
Offline Two-Player Zero-Sum Markov Games with KL Regularization
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；California Institute of Technology（加州理工学院）；University of Virginia（弗吉尼亚大学）；Purdue University（Purdue 大学）；Massachusetts Institute of Technology（麻省理工学院）
Zero-variance control variates (ZV-CV) are a post-processing method to reduce the variance of Monte Carlo estimators of expectations using the derivatives of the log target. Once the derivatives are available, the only additional computational effort lies in solving a linear regression problem. Significant variance reductions have been achieved with this method in low dimensional examples, but the number of covariates in the regression rapidly increases with the dimension of the target. In this paper, we present compelling empirical evidence that the use of penalized regression techniques in t…
Offline and Online KL-Regularized RLHF under Differential Privacy
King Abdullah University of Science and Technology (KAUST)（卡布尔大学科学与技术学院）；Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)（穆罕默德·本·扎耶德人工智能大学）；Massachusetts Institute of Technology (MIT)（麻省理工学院）
Institute of Data Science, National University of Singapore（新加坡国立大学数据科学研究院）；Department of Industrial Systems Engineering and Management, National University of Singapore（新加坡国立大学工业系统工程与管理系）
École Polytechnique（巴黎综合理工学院）；HSE University（高等经济大学）；Google DeepMind（谷歌DeepMind）；Mohamed Bin Zayed University of AI（穆罕默德·本·扎耶德人工智能大学）；IDEMIA（Morpho公司（IDEMIA））；ENS Lyon（里昂高等师范学院）
Technion – Israel Institute of Technology（以色列理工学院）
In the Bayesian reinforcement learning (RL) setting, a prior distribution over the unknown problem parameters -- the rewards and transitions -- is assumed, and a policy that optimizes the (posterior) expected return is sought. A common approximation, which has been recently popularized as meta-RL, is to train the agent on a sample of $N$ problem instances from the prior, with the hope that for large enough $N$, good generalization behavior to an unseen test instance will be obtained. In this work, we study generalization in Bayesian RL under the probably approximately correct (PAC) framework, …
We study model-based offline Reinforcement Learning with general function approximation without a full coverage assumption on the offline data distribution. We present an algorithm named Constrained Pessimistic Policy Optimization (CPPO)which leverages a general function class and uses a constraint over the model class to encode pessimism. Under the assumption that the ground truth model belongs to our function class (i.e., realizability in the function class), CPPO has a PAC guarantee with offline data only providing partial coverage, i.e., it can learn a policy that competes against any poli…
Distribution-Free Confidence Ellipsoids for Ridge Regression with PAC Bounds
Institute for Computer Science；Control (SZTAKI), Hungarian Research Network (HUN-REN), 13-17 Kende utca, H-1111, Budapest, Hungary (e-mail: ).；Department of Probability Theory；Statistics, Institute of Mathematics, E\"otv\"os Lor\'；University (ELTE), 1/C Pázmány Péter sétány, H-1117, Budapest, Hungary (e-mail: )
