English
Related papers

Related papers: f-Divergence constrained policy improvement

200 papers

A key task in managing distributed, sensitive data is to measure the extent to which a distribution changes. Understanding this drift can effectively support a variety of federated learning and analytics tasks. However, in many practical…

Machine Learning · Computer Science 2024-12-02 Mary Scott , Sayan Biswas , Graham Cormode , Carsten Maple

This paper considers reparameterization invariant Bayesian point estimates and credible regions of model parameters for scientific inference and communication. The effect of intrinsic loss function choice in Bayesian intrinsic estimates and…

Methodology · Statistics 2021-09-23 Aki Vehtari

Federated Learning (FL) is a distributed learning approach that trains machine learning models across multiple devices while keeping their local data private. However, FL often faces challenges due to data heterogeneity, leading to…

Machine Learning · Computer Science 2025-10-21 Dun Zeng , Zheshun Wu , Shiyu Liu , Yu Pan , Xiaoying Tang , Zenglin Xu

Standard trust-region methods constrain policy updates via Kullback-Leibler (KL) divergence. However, KL controls only an average divergence and does not directly prevent rare, large likelihood-ratio excursions that destabilize…

Machine Learning · Computer Science 2026-02-09 Gaurish Trivedi , Alakh Sharma , Kartikey Singh Bhandari , Yash Sinha , Pratik Narang , Dhruv Kumar , Jagat Sesh Challa

While reinforcement learning (RL) promises to revolutionize the control of complex nonlinear robotic systems, a profound gap persists between the heuristic success of model-free off-policy deep RL and the underlying theory, which remains…

Machine Learning · Computer Science 2026-05-08 Manuel Haussmann , Mustafa Mert Çelikok , Melih Kandemir

Aligning language models with preferences can be posed as approximating a target distribution representing some desired behavior. Existing approaches differ both in the functional form of the target distribution and the algorithm used to…

Computation and Language · Computer Science 2023-06-07 Dongyoung Go , Tomasz Korbak , Germán Kruszewski , Jos Rozen , Nahyeon Ryu , Marc Dymetman

Recently, continual learning has received a lot of attention. One of the significant problems is the occurrence of \emph{concept drift}, which consists of changing probabilistic characteristics of the incoming data. In the case of the…

Machine Learning · Computer Science 2022-10-11 Sebastián Basterrech , Michal Woźniak

We study the estimation of risk-sensitive policies in reinforcement learning problems defined by a Markov Decision Process (MDPs) whose state and action spaces are countably finite. Prior efforts are predominately afflicted by computational…

Machine Learning · Statistics 2020-03-02 Junyu Zhang , Amrit Singh Bedi , Mengdi Wang , Alec Koppel

In this paper, we investigate the convergence of language models (LMs) trained under different random seeds, measuring convergence as the expected per-token Kullback--Leibler (KL) divergence across seeds. By comparing LM convergence as a…

Computation and Language · Computer Science 2025-10-01 Finlay Fehlauer , Kyle Mahowald , Tiago Pimentel

Large language models (LLMs) have been widely used for problem-solving tasks. Most recent work improves their performance through supervised fine-tuning (SFT) with labeled data or reinforcement learning (RL) from task feedback. In this…

Computation and Language · Computer Science 2025-09-29 Hang Li , Kaiqi Yang , Yucheng Chu , Hui Liu , Jiliang Tang

Policy alignment of large language models refers to constrained policy optimization, where the policy is optimized to maximize a reward while staying close to a reference policy with respect to an $f$-divergence such as the $\mathsf{KL}$…

Machine Learning · Computer Science 2024-06-11 Youssef Mroueh

Complex, high-dimensional data is ubiquitous across many scientific disciplines, including machine learning, biology, and the social sciences. One of the primary methods of visualizing these datasets is with two-dimensional scatter plots…

Machine Learning · Computer Science 2025-10-13 Kiran Smelser , Kaviru Gunaratne , Jacob Miller , Stephen Kobourov

Kalman filtering is a widely used framework for Bayesian estimation. The partitioned update Kalman filter applies a Kalman filter update in parts so that the most linear parts of measurements are applied first. In this paper, we generalize…

Optimization and Control · Mathematics 2016-03-16 Matti Raitoharju , Ángel F. García-Fernández , Robert Piché

We show that the Kullback-Leibler distance is a good measure of the statistical uncertainty of correlation matrices estimated by using a finite set of data. For correlation matrices of multivariate Gaussian variables we analytically…

Data Analysis, Statistics and Probability · Physics 2008-12-02 Michele Tumminello , Fabrizio Lillo , Rosario Nunzio Mantegna

We study the gradient flow for a relaxed approximation to the Kullback-Leibler (KL) divergence between a moving source and a fixed target distribution. This approximation, termed the KALE (KL approximate lower-bound estimator), solves a…

Machine Learning · Statistics 2021-11-01 Pierre Glaser , Michael Arbel , Arthur Gretton

Knowing if a model will generalize to data 'in the wild' is crucial for safe deployment. To this end, we study model disagreement notions that consider the full predictive distribution - specifically disagreement based on Hellinger…

Machine Learning · Computer Science 2023-12-14 Mona Schirmer , Dan Zhang , Eric Nalisnick

In GFlowNets and variational inference, it has been shown that the mean square error between target and model log probabilities is an effective, low variance, surrogate loss for training generative models. This loss has the property that…

Machine Learning · Computer Science 2026-05-18 Jake Fawkes , Jason Hartford

This paper presents new deviation inequalities that are valid uniformly in time under adaptive sampling in a multi-armed bandit model. The deviations are measured using the Kullback-Leibler divergence in a given one-dimensional exponential…

Machine Learning · Statistics 2021-12-09 Emilie Kaufmann , Wouter Koolen

Compared to on-policy counterparts, off-policy model-free deep reinforcement learning can improve data efficiency by repeatedly using the previously gathered data. However, off-policy learning becomes challenging when the discrepancy…

Machine Learning · Computer Science 2023-09-27 Baturay Saglam , Dogan C. Cicek , Furkan B. Mutlu , Suleyman S. Kozat

We consider off-policy temporal-difference (TD) learning methods for policy evaluation in Markov decision processes with finite spaces and discounted reward criteria, and we present a collection of convergence results for several…

Machine Learning · Computer Science 2018-03-30 Huizhen Yu
‹ Prev 1 4 5 6 7 8 10 Next ›