English
Related papers

Related papers: f-Divergence constrained policy improvement

200 papers

Diffusion models are a new class of generative models that revolve around the estimation of the score function associated with a stochastic differential equation. Subsequent to its acquisition, the approximated score function is then…

Statistics Theory · Mathematics 2024-09-13 Giovanni Conforti , Alain Durmus , Marta Gentiloni Silveri

In this paper, we delve deeper into the Kullback-Leibler (KL) Divergence loss and mathematically prove that it is equivalent to the Decoupled Kullback-Leibler (DKL) Divergence loss that consists of 1) a weighted Mean Square Error (wMSE)…

Computer Vision and Pattern Recognition · Computer Science 2024-10-29 Jiequan Cui , Zhuotao Tian , Zhisheng Zhong , Xiaojuan Qi , Bei Yu , Hanwang Zhang

We consider the problem of estimating probability density functions based on sample data, using a finite mixture of densities from some component class. To this end, we introduce the $h$-lifted Kullback--Leibler (KL) divergence as a…

Machine Learning · Statistics 2024-12-24 Mark Chiu Chong , Hien Duy Nguyen , TrungTin Nguyen

Coupling arguments are a central tool for bounding the deviation between two stochastic processes, but traditionally have been limited to Wasserstein metrics. In this paper, we apply the shifted composition rule--an information-theoretic…

Statistics Theory · Mathematics 2024-12-25 Jason M. Altschuler , Sinho Chewi

On-policy reinforcement learning (RL) has become a popular framework for solving sequential decision problems due to its computational efficiency and theoretical simplicity. Some on-policy methods guarantee every policy update is…

Machine Learning · Computer Science 2023-12-12 K. R. Zentner , Ujjwal Puri , Zhehui Huang , Gaurav S. Sukhatme

Recent work shows that preference alignment objectives can be interpreted as divergence estimators between aligned (preferred) & unaligned (less-preferred) distributions, yielding a principled recipe for designing alignment losses. However,…

Machine Learning · Computer Science 2026-05-12 Rajdeep Haldar , Lantao Mei , Guang Lin , Yue Xing , Qifan Song

The Kullback-Leibler (KL) divergence is a fundamental equation of information theory that quantifies the proximity of two probability distributions. Although difficult to understand by examining the equation, an intuition and understanding…

Information Theory · Computer Science 2014-04-09 Jonathon Shlens

Divergences are quantities that measure discrepancy between two probability distributions and play an important role in various fields such as statistics and machine learning. Divergences are non-negative and are equal to zero if and only…

Statistics Theory · Mathematics 2019-10-22 Tomohiro Nishiyama

Policy optimization, which finds the desired policy by maximizing value functions via optimization techniques, lies at the heart of reinforcement learning (RL). In addition to value maximization, other practical considerations arise as…

Machine Learning · Computer Science 2023-01-12 Wenhao Zhan , Shicong Cen , Baihe Huang , Yuxin Chen , Jason D. Lee , Yuejie Chi

Estimating Kullback Leibler (KL) divergence from samples of two distributions is essential in many machine learning problems. Variational methods using neural network discriminator have been proposed to achieve this task in a scalable…

Machine Learning · Computer Science 2021-10-01 Sandesh Ghimire , Aria Masoomi , Jennifer Dy

The problem of estimating the Kullback-Leibler divergence $D(P\|Q)$ between two unknown distributions $P$ and $Q$ is studied, under the assumption that the alphabet size $k$ of the distributions can scale to infinity. The estimation is…

Information Theory · Computer Science 2018-02-22 Yuheng Bu , Shaofeng Zou , Yingbin Liang , Venugopal V. Veeravalli

Change of measure inequalities translate divergences between probability measures into explicit bounds on event probabilities, and play an important role in deriving probabilistic guarantees in learning theory, information theory, and…

Information Theory · Computer Science 2026-05-28 Yanxiao Liu , Yijun Fan , Deniz Gündüz

Policy optimization methods like Group Relative Policy Optimization (GRPO) and its variants have achieved strong results on mathematical reasoning and code generation tasks. Despite extensive exploration of reward processing strategies and…

Machine Learning · Computer Science 2026-02-05 Rui Yuan , Mykola Khandoga , Vinay Kumar Sankarapu

The generalized Kullback-Leibler divergence (K-Ld) in Tsallis statistics [constrained by the additive duality of generalized statistics (dual generalized K-Ld)] is here reconciled with the theory of Bregman divergences for expectations…

Statistical Mechanics · Physics 2015-05-27 R. C. Venkatesan , A. Plastino

The performance of machine learning classification algorithms are evaluated by estimating metrics, often from the confusion matrix, using training data and cross-validation. However, these do not prove that the best possible performance has…

Machine Learning · Statistics 2024-03-05 L. Crow , S. J. Watts

Transfer learning, or domain adaptation, is concerned with machine learning problems in which training and testing data come from possibly different distributions (denoted as $\mu$ and $\mu'$, respectively). In this work, we give an…

Machine Learning · Computer Science 2020-05-20 Xuetong Wu , Jonathan H. Manton , Uwe Aickelin , Jingge Zhu

\emph{Kullback-Leibler} (KL) regularization is ubiquitous in reinforcement learning algorithms in the form of \emph{reverse} or \emph{forward} KL. Recent studies have demonstrated $\epsilon^{-1}$-type fast rates for decision making under…

Machine Learning · Computer Science 2026-05-12 Qingyue Zhao , Kaixuan Ji , Heyang Zhao , Quanquan Gu

Language model (LM) alignment improves model outputs to reflect human preferences while preserving the capabilities of the base model. The most common alignment approaches are (i) reinforcement learning, which maximizes the expected reward…

Machine Learning · Computer Science 2026-05-11 Lucas Monteiro Paes , Natalie Mackraz , Barry-John Theobald , Federico Danieli

Inferring and comparing complex, multivariable probability density functions is fundamental to problems in several fields, including probabilistic learning, network theory, and data analysis. Classification and prediction are the two faces…

Information Theory · Computer Science 2017-03-30 David J. Galas , T. Gregory Dewey , James Kunert-Graf , Nikita A. Sakhanenko

We present and analyze the Krylov-Bellman Boosting (KBB) algorithm for policy evaluation in general state spaces. It alternates between fitting the Bellman residual using non-parametric regression (as in boosting), and estimating the value…

Machine Learning · Statistics 2023-03-28 Eric Xia , Martin J. Wainwright