English
Related papers

Related papers: A Simpler Alternative to Variational Regularized C…

200 papers

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an indispensable paradigm for enhancing reasoning in Large Language Models (LLMs). However, standard policy optimization methods, such as Group Relative Policy…

Machine Learning · Computer Science 2026-02-09 Pengyi Li , Elizaveta Goncharova , Andrey Kuznetsov , Ivan Oseledets

We establish a new concentration result for regularized risk minimizers which is similar to an oracle inequality. Applying this inequality to regularized least squares minimizers like least squares support vector machines, we show that…

Statistics Theory · Mathematics 2007-06-13 Ingo Steinwart , Don Hush , Clint Scovel

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

In domains such as finance, healthcare, and robotics, managing worst-case scenarios is critical, as failure to do so can lead to catastrophic outcomes. Distributional Reinforcement Learning (DRL) provides a natural framework to incorporate…

Machine Learning · Computer Science 2026-02-13 Mehrdad Moghimi , Hyejin Ku

In this paper, we aim to utilize only offline trajectory data to train a policy for multi-objective RL. We extend the offline policy-regularized method, a widely-adopted approach for single-objective offline RL problems, into the…

Machine Learning · Computer Science 2024-01-05 Qian Lin , Chao Yu , Zongkai Liu , Zifan Wu

Reinforcement learning (RL) post-training has increasingly demonstrated strong ability to elicit reasoning behaviors in large language models (LLMs). For training efficiency, rollouts are typically generated in an off-policy manner using an…

Artificial Intelligence · Computer Science 2026-02-02 Shiye Lei , Zhihao Cheng , Dacheng Tao

The field of risk-constrained reinforcement learning (RCRL) has been developed to effectively reduce the likelihood of worst-case scenarios by explicitly handling risk-measure-based constraints. However, the nonlinearity of risk measures…

Machine Learning · Computer Science 2024-05-30 Dohyeong Kim , Taehyun Cho , Seungyub Han , Hojun Chung , Kyungjae Lee , Songhwai Oh

Conformal prediction (CP) is a distribution-free framework for achieving probabilistic guarantees on black-box models. CP is generally applied to a model post-training. Recent research efforts, on the other hand, have focused on optimizing…

Machine Learning · Computer Science 2025-02-11 Sima Noorani , Orlando Romero , Nicolo Dal Fabbro , Hamed Hassani , George J. Pappas

Group-Relative Policy Optimization (GRPO) has emerged as the standard for training reasoning capabilities in large language models through reinforcement learning. By estimating advantages using group-mean rewards rather than a learned…

Artificial Intelligence · Computer Science 2026-03-06 Anisha Garg , Claire Zhang , Nishit Neema , David Bick , Ganesh Venkatesh , Joel Hestness

Performative prediction is a framework accounting for the shift in the data distribution induced by the prediction of a model deployed in the real world. Ensuring rapid convergence to a stable solution where the data distribution remains…

Machine Learning · Computer Science 2026-01-30 Pedram Khorsandi , Rushil Gupta , Mehrnaz Mofakhami , Simon Lacoste-Julien , Gauthier Gidel

We consider the problem of selecting a subset of points from a dataset of $n$ unlabeled examples for labeling, with the goal of training a multiclass classifier. To address this, we build upon the regret minimization framework introduced by…

Machine Learning · Computer Science 2026-02-27 Youguang Chen , George Biros

The main challenge of offline reinforcement learning, where data is limited, arises from a sequence of counterfactual reasoning dilemmas within the realm of potential actions: What if we were to choose a different course of action? These…

Machine Learning · Computer Science 2024-05-22 Yao Liu , Pratik Chaudhari , Rasool Fakoor

Offline reinforcement learning (RL) methods aim to learn optimal policies with access only to trajectories in a fixed dataset. Policy constraint methods formulate policy learning as an optimization problem that balances maximizing reward…

Machine Learning · Computer Science 2025-03-04 Padmanaba Srinivasan , William Knottenbelt

Many practical applications of reinforcement learning (RL) constrain the agent to learn from a fixed offline dataset of logged interactions, which has already been gathered, without offering further possibility for data collection. However,…

Machine Learning · Computer Science 2021-07-06 Zizhou Su

We consider the problem of learning the best possible policy from a fixed dataset, known as offline Reinforcement Learning (RL). A common taxonomy of existing offline RL works is policy regularization, which typically constrains the learned…

Machine Learning · Computer Science 2023-08-16 Yuhang Ran , Yi-Chen Li , Fuxiang Zhang , Zongzhang Zhang , Yang Yu

In partially observable (PO) environments, deep reinforcement learning (RL) agents often suffer from unsatisfactory performance, since two problems need to be tackled together: how to extract information from the raw observations to solve…

Machine Learning · Computer Science 2019-12-25 Dongqi Han , Kenji Doya , Jun Tani

Deep learning models excel in computer vision tasks but often fail to generalize to out-of-distribution (OOD) domains. Invariant Risk Minimization (IRM) aims to address OOD generalization by learning domain-invariant features. However, IRM…

Computer Vision and Pattern Recognition · Computer Science 2025-01-24 Yaoyao Zhu , Xiuding Cai , Yingkai Wang , Dong Miao , Zhongliang Fu , Xu Luo

Conventional techniques for supervised classification constrain the classification rules considered and use surrogate losses for classification 0-1 loss. Favored families of classification rules are those that enjoy parametric…

Machine Learning · Statistics 2019-06-03 Santiago Mazuelas , Andrea Zanoni , Aritz Perez

We introduce an alternative closed form lower bound on the Gaussian process ($\mathcal{GP}$) likelihood based on the R\'enyi $\alpha$-divergence. This new lower bound can be viewed as a convex combination of the Nystr\"om approximation and…

Machine Learning · Statistics 2023-07-04 Xubo Yue , Raed Kontar

Backward error analysis allows finding a modified loss function, which the parameter updates really follow under the influence of an optimization method. The additional loss terms included in this modified function is called implicit…

Machine Learning · Computer Science 2025-03-06 Jinwoo Lim , Suhyun Kim , Soo-Mook Moon