English
Related papers

Related papers: f-Divergence constrained policy improvement

200 papers

In deep reinforcement learning, policy optimization methods need to deal with issues such as function approximation and the reuse of off-policy data. Standard policy gradient methods do not handle off-policy data well, leading to premature…

Machine Learning · Computer Science 2025-01-28 Qing Wang , Yingru Li , Jiechao Xiong , Tong Zhang

Temporal-difference learning (TD), coupled with neural networks, is among the most fundamental building blocks of deep reinforcement learning. However, due to the nonlinearity in value function approximation, such a coupling leads to…

Machine Learning · Computer Science 2020-04-16 Qi Cai , Zhuoran Yang , Jason D. Lee , Zhaoran Wang

The powerful cooperation of federated learning (FL) and differential privacy~(DP) provides a promising paradigm for the large-scale private clients. However, existing analyses in FL-DP mostly rely on the composition theorem and cannot…

Machine Learning · Computer Science 2026-05-14 Yan Sun , Qixin Zhang , Li Shen , Dacheng Tao

We consider the fundamental problem of estimating a discrete distribution on a domain of size $K$ with high probability in Kullback-Leibler divergence. We provide upper and lower bounds on the minimax estimation rate, which show that the…

Machine Learning · Statistics 2026-02-23 Dirk van der Hoeven , Julia Olkhovskaia , Tim van Erven

In many real-world settings, reinforcement learning systems suffer performance degradation when the environment encountered at deployment differs from that observed during training. Distributionally robust reinforcement learning (DR-RL)…

Machine Learning · Computer Science 2026-03-05 Debamita Ghosh , George K. Atia , Yue Wang

A central paradox in fine-tuning Large Language Models (LLMs) with Reinforcement Learning with Verifiable Reward (RLVR) is the frequent degradation of multi-attempt performance (Pass@k) despite improvements in single-attempt accuracy…

Machine Learning · Computer Science 2026-03-04 Long Li , Zhijian Zhou , Jiaran Hao , Jason Klein Liu , Yanting Miao , Wei Pang , Xiaoyu Tan , Wei Chu , Zhe Wang , Shirui Pan , Chao Qu , Yuan Qi

We generalise the classical Pinsker inequality which relates variational divergence to Kullback-Liebler divergence in two ways: we consider arbitrary f-divergences in place of KL divergence, and we assume knowledge of a sequence of values…

Information Theory · Computer Science 2009-06-09 Mark D. Reid , Robert C. Williamson

Diffusion models have achieved great success in generating high-dimensional samples across various applications. While the theoretical guarantees for continuous-state diffusion models have been extensively studied, the convergence analysis…

Machine Learning · Computer Science 2025-04-15 Zikun Zhang , Zixiang Chen , Quanquan Gu

The analysis of Temporal Difference (TD) learning in the average-reward setting faces notable theoretical difficulties because the Bellman operator is not contractive with respect to any norm. This complicates standard analyses of…

Machine Learning · Computer Science 2026-05-05 Haoxing Tian , Zaiwei Chen , Ioannis Ch. Paschalidis , Alex Olshevsky

We consider the problem of parameter estimation in a Bayesian setting and propose a general lower-bound that includes part of the family of $f$-Divergences. The results are then applied to specific settings of interest and compared to other…

Information Theory · Computer Science 2022-05-19 Adrien Vandenbroucque , Amedeo Roberto Esposito , Michael Gastpar

In this work, the probability of an event under some joint distribution is bounded by measuring it with the product of the marginals instead (which is typically easier to analyze) together with a measure of the dependence between the two…

Information Theory · Computer Science 2020-10-22 Amedeo Roberto Esposito , Michael Gastpar , Ibrahim Issa

In this paper, some new upper bounds for Kullback-Leibler divergence(KL-divergence) based on $L^1, L^2$ and $L^\infty$ norms of density functions are discussed. Our findings unveil that the convergence in KL-divergence sense sandwiches…

Probability · Mathematics 2024-10-31 Liuquan Yao , Songhao Liu

Reinforcement learning (RL) has become a cornerstone for fine-tuning Large Language Models (LLMs), with Proximal Policy Optimization (PPO) serving as the de facto standard algorithm. Despite its ubiquity, we argue that the core ratio…

Machine Learning · Computer Science 2026-05-27 Penghui Qi , Xiangxin Zhou , Zichen Liu , Tianyu Pang , Chao Du , Min Lin , Wee Sun Lee

The reasoning performance of large language models (LLMs) can be substantially improved by training them with reinforcement learning (RL). The RL objective for LLM training involves a regularization term, which is the reverse…

Kullback-Leiber divergence has been widely used in Knowledge Distillation (KD) to compress Large Language Models (LLMs). Contrary to prior assertions that reverse Kullback-Leibler (RKL) divergence is mode-seeking and thus preferable over…

Computation and Language · Computer Science 2024-12-10 Taiqiang Wu , Chaofan Tao , Jiahao Wang , Runming Yang , Zhe Zhao , Ngai Wong

A stream of algorithmic advances has steadily increased the popularity of the Bayesian approach as an inference paradigm, both from the theoretical and applied perspective. Even with apparent successes in numerous application fields, a…

Methodology · Statistics 2020-07-10 Owen Thomas , Henri Pesonen , Jukka Corander

The increasing capabilities of large language models (LLMs) raise opportunities for artificial general intelligence but concurrently amplify safety concerns, such as potential misuse of AI systems, necessitating effective AI alignment.…

Machine Learning · Computer Science 2023-09-29 Chaoqi Wang , Yibo Jiang , Chenghao Yang , Han Liu , Yuxin Chen

Knowledge distillation (KD), transferring knowledge from a cumbersome teacher model to a lightweight student model, has been investigated to design efficient neural architectures. Generally, the objective function of KD is the…

Machine Learning · Computer Science 2021-05-20 Taehyeon Kim , Jaehoon Oh , NakYil Kim , Sangwook Cho , Se-Young Yun

In this work we introduce a family of transformations, named \textit{divergence transformations}, interpolating between any pair of probability density functions sharing the same support. We prove the remarkable property that the whole…

Mathematical Physics · Physics 2025-12-15 Razvan Gabriel Iagar , David Puertas-Centeno , Elio V. Toranzo

Several scalable sample-based methods to compute the Kullback Leibler (KL) divergence between two distributions have been proposed and applied in large-scale machine learning models. While they have been found to be unstable, the…

Machine Learning · Computer Science 2021-09-07 Sandesh Ghimire , Prashnna K Gyawali , Linwei Wang