paper-with-me

홈 › Papers

Non-vacuous Generalization Bounds for Reinforcement Learning with Verifiable Rewards

2026-07-16 · Yuxuan Zhu, Rohan Alur, Daniel Kang arxiv

While reinforcement learning with verifiable rewards (RLVR) is widely used to improve the reasoning capabilities of large language models (LLMs), the generalizability of the resulting models remains poorly understood. In this work, we establish the first non-vacuous generalization bounds for parameter-efficient RLVR fine-tuning at the billion-parameter scale. Our approach adapts PAC-Bayes compression bounds to this setting, and addresses the inherent stochasticity of token generation by applying the Gumbel-max reparameterization trick. To operationalize these bounds, we propose the Progressive RLVR framework, which integrates RLVR with on-policy distillation, TinyLoRA, and model quantization. Progressive RLVR empirically retains 84-97% performance of standard LoRA fine-tuning while producing models that are 14,796x more compressible. We show that this framework yields non-vacuous generalization bounds in four domains: mathematical problem-solving, programming, general-knowledge reasoning, and Text-to-SQL. Our bounds exceed the accuracy of the base model by 9-51% and lie within 6-11% of the accuracy of the fine-tuned models.

📄 PDF Abstract BibTeX arXiv:2607.14506

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

A Generalization Bound for Nearly-Linear Networks

2024-07-09 · Eugene Golikov

We consider nonlinear networks as perturbations of linear ones. Based on this approach, we present novel generalization bounds that become non-vacuous for networks that are close to being linear. The main advantage over …

Generalization Bounds

Non-Vacuous Generalization Bounds for Large Language Models

2023-12-28 · Sanae Lotfi, Marc Finzi, Yilun Kuang, Tim G. J. Rudner 외

Modern language models can contain billions of parameters, raising the question of whether they can generalize beyond the training data or simply parrot their training corpora. We provide the first non-vacuous generaliza…

Generalization Boundsvalid

Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data

2017-03-31 · Gintare Karolina Dziugaite, Daniel M. Roy

One of the defining properties of deep learning is that models are chosen to have many more parameters than available training data. In light of this capacity for overfitting, it is remarkable that simple algorithms like…

Generalization Bounds

Unlocking Tokens as Data Points for Generalization Bounds on Larger Language Models

2024-07-25 · Sanae Lotfi, Yilun Kuang, Brandon Amos, Micah Goldblum 외

Large language models (LLMs) with billions of parameters excel at predicting the next token in a sequence. Recent work computes non-vacuous compression-based generalization bounds for LLMs, but these bounds are vacuous f…

Generalization BoundsQuantization

Rethinking Reinforcement Fine-Tuning in LVLM: Convergence, Reward Decomposition, and Generalization

2026-04-21 · Carter Adams, Rafael Oliveira, Gabriel Almeida, Sofia Torres arxiv

Reinforcement fine-tuning with verifiable rewards (RLVR) has emerged as a powerful paradigm for equipping large vision-language models (LVLMs) with agentic capabilities such as tool use and multi-step reasoning. Despite …