English
Related papers

Related papers: Leverage the Average: an Analysis of KL Regulariza…

200 papers

Under mild assumptions on the kernel, we obtain the best known error rates in a regularized learning scenario taking place in the corresponding reproducing kernel Hilbert space (RKHS). The main novelty in the analysis is a proof that one…

Statistics Theory · Mathematics 2010-01-14 Shahar Mendelson , Joseph Neeman

We theoretically investigate the convergence rate and support consistency (i.e., correctly identifying the subset of non-zero coefficients in the large sample limit) of multiple kernel learning (MKL). We focus on MKL with block-l1…

Machine Learning · Statistics 2011-07-29 Taiji Suzuki , Ryota Tomioka , Masashi Sugiyama

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…

Machine Learning · Computer Science 2021-09-27 Aviv Tamar , Daniel Soudry , Ev Zisselman

In this paper, we give a new generalization error bound of Multiple Kernel Learning (MKL) for a general class of regularizations, and discuss what kind of regularization gives a favorable predictive accuracy. Our main target in this paper…

Machine Learning · Statistics 2011-11-17 Taiji Suzuki

Reinforcement learning (RL) combines a control problem with statistical estimation: The system dynamics are not known to the agent, but can be learned through experience. A recent line of research casts `RL as inference' and suggests a…

Machine Learning · Computer Science 2020-11-05 Brendan O'Donoghue , Ian Osband , Catalin Ionescu

Incorporating expert demonstrations has empirically helped to improve the sample efficiency of reinforcement learning (RL). This paper quantifies theoretically to what extent this extra information reduces RL's sample complexity. In…

Reinforcement Learning with Verifiable Rewards (RLVR) strengthens LLM reasoning, but training often oscillates between {entropy collapse} and {entropy explosion}. We trace both hazards to the mean baseline used in value-free RL (e.g., GRPO…

Machine Learning · Computer Science 2026-03-03 Junkang Wu , Kexin Huang , Jiancan Wu , An Zhang , Xiang Wang , Xiangnan He

Regularization is used to find a solution that both fits the data and is sufficiently smooth, and thereby is very effective for designing and refining learning algorithms. But the influence of its exponent remains poorly understood. In…

Machine Learning · Statistics 2016-12-15 Julien Audiffren , Hachem Kadri

Reinforcement Learning with Verified Reward (RLVR) has emerged as a critical paradigm for advancing the reasoning capabilities of Large Language Models (LLMs). Most existing RLVR methods, such as GRPO and its variants, ensure stable updates…

Machine Learning · Computer Science 2026-02-10 Qingyuan Wu , Yuhui Wang , Simon Sinong Zhan , Yanning Dai , Shilong Deng , Sarra Habchi , Qi Zhu , Matthias Gallé , Chao Huang

The gloabal objective of inverse Reinforcement Learning (IRL) is to estimate the unknown cost function of some MDP base on observed trajectories generated by (approximate) optimal policies. The classical approach consists in tuning this…

Machine Learning · Computer Science 2021-05-26 Firas Jarboui , Vianney Perchet

Deep Reinforcement Learning (RL) powered by neural net approximation of the Q function has had enormous empirical success. While the theory of RL has traditionally focused on linear function approximation (or eluder dimension) approaches,…

Machine Learning · Computer Science 2021-12-28 Baihe Huang , Kaixuan Huang , Sham M. Kakade , Jason D. Lee , Qi Lei , Runzhe Wang , Jiaqi Yang

This paper presents a review of the field of reinforcement learning (RL), with a focus on providing a comprehensive overview of the key concepts, techniques, and algorithms for beginners. RL has a unique setting, jargon, and mathematics…

Machine Learning · Computer Science 2023-04-04 Mohamed-Amine Chadi , Hajar Mousannif

Online interactions with the environment to collect data samples for training a Reinforcement Learning (RL) agent is not always feasible due to economic and safety concerns. The goal of Offline Reinforcement Learning is to address this…

Machine Learning · Computer Science 2021-10-05 Chi Zhang , Sanmukh Rao Kuppannagari , Viktor K Prasanna

Linear regression is a widely used technique to fit linear models and finds widespread applications across different areas such as machine learning and statistics. In most real-world scenarios, however, linear regression problems are often…

Quantum Physics · Physics 2023-05-02 Shantanav Chakraborty , Aditya Morolia , Anurudh Peduri

We study the problem of nonnegative rank-one approximation of a nonnegative tensor, and show that the globally optimal solution that minimizes the generalized Kullback-Leibler divergence can be efficiently obtained, i.e., it is not NP-hard.…

Signal Processing · Electrical Eng. & Systems 2017-11-22 Kejun Huang , Nicholas D. Sidiropoulos

Prior knowledge on properties of a target model often come as discrete or combinatorial descriptions. This work provides a unified computational framework for defining norms that promote such structures. More specifically, we develop…

Machine Learning · Statistics 2019-04-11 Amin Jalali , Adel Javanmard , Maryam Fazel

Transfer learning, or domain adaptation, is concerned with machine learning problems in which training and testing data come from possibly different probability distributions. In this work, we give an information-theoretic analysis of the…

Information Theory · Computer Science 2024-08-09 Xuetong Wu , Jonathan H. Manton , Uwe Aickelin , Jingge Zhu

In representation learning (RL), how to make the learned representations easy to interpret and less overfitted to training data are two important but challenging issues. To address these problems, we study a new type of regulariza- tion…

Machine Learning · Computer Science 2017-11-28 Pengtao Xie , Hongbao Zhang , Eric P. Xing

In optimization for Machine learning (ML), it is typical that curvature-matrix (CM) estimates rely on an exponential average (EA) of local estimates (giving EA-CM algorithms). This approach has little principled justification, but is very…

Machine Learning · Computer Science 2022-07-01 Constantin Octavian Puiu

Reinforcement learning (RL) is frequently employed in fine-tuning large language models (LMs), such as GPT-3, to penalize them for undesirable features of generated sequences, such as offensiveness, social bias, harmfulness or falsehood.…

Machine Learning · Computer Science 2022-10-24 Tomasz Korbak , Ethan Perez , Christopher L Buckley