paper-with-me

Papers

Towards Sharper Information-theoretic Generalization Bounds for Meta-Learning

2025-01-26 · Wen Wen, Tieliang Gong, Yuxin Dong, Yong-Jin Liu, Weizhan Zhang

In recent years, information-theoretic generalization bounds have emerged as a promising approach for analyzing the generalization capabilities of meta-learning algorithms. However, existing results are confined to two-step bounds, failing to provide a sharper characterization of the meta-generalization gap that simultaneously accounts for environment-level and task-level dependencies. This paper addresses this fundamental limitation by establishing novel single-step information-theoretic bounds for meta-learning. Our bounds exhibit substantial advantages over prior MI- and CMI-based bounds, especially in terms of tightness, scaling behavior associated with sampled tasks and samples per task, and computational tractability. Furthermore, we provide novel theoretical insights into the generalization behavior of two classes of noise and iterative meta-learning algorithms via gradient covariance analysis, where the meta-learner uses either the entire meta-training data (e.g., Reptile), or separate training and test data within the task (e.g., model agnostic meta-learning (MAML)). Numerical results validate the effectiveness of the derived bounds in capturing the generalization dynamics of meta-learning.

📄 PDF Abstract BibTeX arXiv:2501.15559

Code (0)

등록된 구현이 없습니다.

Tasks

Generalization BoundsMeta-Learning

Similar Papers 제목 키워드 기반

Sample-Conditioned Hypothesis Stability Sharpens Information-Theoretic Generalization Bounds

2023-10-31 · NeurIPS 2023 11

We present new information-theoretic generalization guarantees through the a novel construction of the "neighboring-hypothesis" matrix and a new family of stability notions termed sample-conditioned hypothesis (SCH) stab…

Generalization Bounds

Stability Based Generalization Bounds for Exponential Family Langevin Dynamics

2022-01-09 · Arindam Banerjee, Tiancong Chen, Xinyan Li, Yingxue Zhou

Recent years have seen advances in generalization bounds for noisy stochastic algorithms, especially stochastic gradient Langevin dynamics (SGLD) based on stability (Mou et al., 2018; Li et al., 2020) and information the…

Generalization Bounds

Sharper Generalization Bounds for Transformer

2026-03-23 · Yawen Li, Tao Hu, Zhouhui Lian, Wan Tian 외 arxiv

This paper studies generalization error bounds for Transformer models. Based on the offset Rademacher complexity, we derive sharper generalization bounds for different Transformer architectures, including single-layer si…

$L_2$-Uniform Stability of Randomized Learning Algorithms: Sharper Generalization Bounds and Confidence Boosting

2023-09-21 · NeurIPS 2023 11

Exponential generalization bounds with near-optimal rates have recently been established for uniformly stable algorithms~\citep{feldman2019high,bousquet2020sharper}. We seek to extend these best known high probability bo…

An Information-Theoretic Analysis of OOD Generalization in Meta-Reinforcement Learning

2025-10-27 · Xingtu Liu arxiv

In this work, we study out-of-distribution (OOD) generalization in meta-reinforcement learning from an information-theoretic perspective. We begin by establishing OOD generalization bounds for meta-supervised learning un…

Reinforcement Learning