English
Related papers

Related papers: From Data to Rewards: a Bilevel Optimization Persp…

200 papers

We introduce LLaVA-Reward, an efficient reward model designed to automatically evaluate text-to-image (T2I) generations across multiple perspectives, leveraging pretrained multimodal large language models (MLLMs). Existing MLLM-based…

Computer Vision and Pattern Recognition · Computer Science 2025-07-31 Shijie Zhou , Ruiyi Zhang , Huaisheng Zhu , Branislav Kveton , Yufan Zhou , Jiuxiang Gu , Jian Chen , Changyou Chen

We study the feature-based newsvendor problem, in which a decision-maker has access to historical data consisting of demand observations and exogenous features. In this setting, we investigate feature selection, aiming to derive sparse,…

Machine Learning · Computer Science 2022-09-13 Breno Serrano , Stefan Minner , Maximilian Schiffer , Thibaut Vidal

Reinforcement learning algorithms in multi-agent systems deliver highly resilient and adaptable solutions for common problems in telecommunications,aerospace, and industrial robotics. However, achieving an optimal global goal remains a…

Multiagent Systems · Computer Science 2021-05-18 Changgang Zheng , Shufan Yang , Juan Parra-Ullauri , Antonio Garcia-Dominguez , Nelly Bencomo

Large neural networks pretrained on web-scale corpora are central to modern machine learning. In this paradigm, the distribution of the large, heterogeneous pretraining data rarely matches that of the application domain. This work considers…

Machine Learning · Computer Science 2023-11-21 David Grangier , Pierre Ablin , Awni Hannun

In recent years, by leveraging more data, computation, and diverse tasks, learned optimizers have achieved remarkable success in supervised learning, outperforming classical hand-designed optimizers. Reinforcement learning (RL) is…

Machine Learning · Computer Science 2024-06-05 Qingfeng Lan , A. Rupam Mahmood , Shuicheng Yan , Zhongwen Xu

Reinforcement learning with verifiable reward has recently emerged as a central paradigm for post-training large language models (LLMs); however, prevailing mean-based methods, such as Group Relative Policy Optimization (GRPO), suffer from…

Machine Learning · Computer Science 2025-10-02 Tao Ren , Jinyang Jiang , Hui Yang , Wan Tian , Minhao Zou , Guanghao Li , Zishi Zhang , Qinghao Wang , Shentao Qin , Yanjun Zhao , Rui Tao , Hui Shao , Yijie Peng

This paper investigates the so-called reward-balancing methods, a novel class of algorithms for solving discounted-return reinforcement learning (RL) problems. These methods consist of iteratively adjusting the reward function to transform…

Optimization and Control · Mathematics 2026-04-23 Simone Baroncini , Bahman Gharesifard , Giuseppe Notarstefano

A promising way to improve the sample efficiency of reinforcement learning is model-based methods, in which many explorations and evaluations can happen in the learned models to save real-world samples. However, when the learned model has a…

Machine Learning · Computer Science 2022-09-14 Haoxin Lin , Yihao Sun , Jiaji Zhang , Yang Yu

We study a common challenge in reinforcement learning for large language models (LLMs): the Zero-Reward Assumption, where non-terminal actions (i.e., intermediate token generations) receive zero task-specific immediate reward, while only…

Machine Learning · Computer Science 2025-06-04 Shenghua He , Tian Xia , Xuan Zhou , Hui Wei

Existing alignment methods share a common topology of information flow, where reward information is collected from humans, modeled with preference learning, and used to tune language models. However, this shared topology has not been…

Machine Learning · Computer Science 2025-05-29 Tianyi Qiu , Fanzhi Zeng , Jiaming Ji , Dong Yan , Kaile Wang , Jiayi Zhou , Yang Han , Josef Dai , Xuehai Pan , Yaodong Yang

We present a novel regularization approach to train neural networks that enjoys better generalization and test error than standard stochastic gradient descent. Our approach is based on the principles of cross-validation, where a validation…

Computer Vision and Pattern Recognition · Computer Science 2018-09-06 Simon Jenni , Paolo Favaro

Gradient-based learning in multi-agent systems is difficult because the gradient derives from a first-order model which does not account for the interaction between agents' learning processes. LOLA (arXiv:1709.04326) accounts for this by…

Machine Learning · Computer Science 2023-12-12 Tim Cooijmans , Milad Aghajohari , Aaron Courville

Reinforcement learning (RL) algorithms assume that users specify tasks by manually writing down a reward function. However, this process can be laborious and demands considerable technical expertise. Can we devise RL algorithms that instead…

Machine Learning · Computer Science 2022-01-03 Benjamin Eysenbach , Sergey Levine , Ruslan Salakhutdinov

Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for Large Language Model (LLM) reasoning, yet current methods face key challenges in resource allocation and policy optimization dynamics: (i) uniform rollout…

Machine Learning · Computer Science 2026-04-24 Yangyi Fang , Jiaye Lin , Xiaoliang Fu , Cong Qin , Haolin Shi , Chaowen Hu , Lu Pan , Ke Zeng , Xunliang Cai

We study estimation and statistical inference for reward models used in aligning large language models (LLMs). A key component of LLM alignment is reinforcement learning from human feedback (RLHF), where humans compare pairs of…

Machine Learning · Statistics 2025-12-04 Pangpang Liu , Junwei Lu , Will Wei Sun

For over a decade, model-based reinforcement learning has been seen as a way to leverage control-based domain knowledge to improve the sample-efficiency of reinforcement learning agents. While model-based agents are conceptually appealing,…

Machine Learning · Computer Science 2021-05-28 Brandon Amos , Samuel Stanton , Denis Yarats , Andrew Gordon Wilson

Reward modelling from preference data is a crucial step in aligning large language models (LLMs) with human values, requiring robust generalisation to novel prompt-response pairs. In this work, we propose to frame this problem in a causal…

Artificial Intelligence · Computer Science 2026-05-12 Katarzyna Kobalczyk , Mihaela van der Schaar

Bilevel optimization and bilevel minimax optimization have recently emerged as unifying frameworks for a range of machine-learning tasks, including hyperparameter optimization and reinforcement learning. The existing literature focuses on…

Machine Learning · Computer Science 2026-04-23 Xuelin Zhang , Peipei Yuan

Manipulating data, such as weighting data examples or augmenting with new instances, has been increasingly used to improve model training. Previous work has studied various rule- or learning-based approaches designed for specific types of…

Machine Learning · Computer Science 2019-10-29 Zhiting Hu , Bowen Tan , Ruslan Salakhutdinov , Tom Mitchell , Eric P. Xing

From a first-principles perspective, it may seem odd that the strongest results in foundation model fine-tuning (FT) are achieved via a relatively complex, two-stage training procedure. Specifically, one first trains a reward model (RM) on…

Machine Learning · Computer Science 2025-10-20 Gokul Swamy , Sanjiban Choudhury , Wen Sun , Zhiwei Steven Wu , J. Andrew Bagnell