paper-with-me

홈 › Papers

Instance-Dependent Generalization Bounds via Optimal Transport

2022-11-02 · Songyan Hou, Parnian Kassraie, Anastasis Kratsios, Andreas Krause, Jonas Rothfuss

Existing generalization bounds fail to explain crucial factors that drive the generalization of modern neural networks. Since such bounds often hold uniformly over all parameters, they suffer from over-parametrization and fail to account for the strong inductive bias of initialization and stochastic gradient descent. As an alternative, we propose a novel optimal transport interpretation of the generalization problem. This allows us to derive instance-dependent generalization bounds that depend on the local Lipschitz regularity of the learned prediction function in the data space. Therefore, our bounds are agnostic to the parametrization of the model and work well when the number of training samples is much smaller than the number of parameters. With small modifications, our approach yields accelerated rates for data on low-dimensional manifolds and guarantees under distribution shifts. We empirically analyze our generalization bounds for neural networks, showing that the bound values are meaningful and capture the effect of popular regularization methods during training.

📄 PDF Abstract BibTeX arXiv:2211.01258

Code (0)

등록된 구현이 없습니다.

Tasks

Generalization BoundsInductive Bias

Methods 이 논문이 사용한 방법론

fail 설명 없음

Similar Papers 제목 키워드 기반

Measuring Generalization with Optimal Transport

2021-06-07 · NeurIPS 2021 12 · Ching-Yao Chuang, Youssef Mroueh, Kristjan Greenewald, Antonio Torralba 외

Understanding the generalization of deep neural networks is one of the most important tasks in deep learning. Although much progress has been made, theoretical error bounds still often behave disparately from empirical o…

Generalization Bounds

An Optimal Transport View on Generalization

2018-11-08 · Jingwei Zhang, Tongliang Liu, DaCheng Tao

We derive upper bounds on the generalization error of learning algorithms based on their \emph{algorithmic transport cost}: the expected Wasserstein distance between the output hypothesis and the output hypothesis condit…

Learning Theory

Transductive Generalization via Optimal Transport and Its Application to Graph Node Classification

2026-03-10 · MoonJeong Park, Seungbeom Lee, Kyungmin Kim, Jaeseung Heo 외 arxiv

Many existing transductive bounds rely on classical complexity measures that are computationally intractable and often misaligned with empirical behavior. In this work, we establish new representation-based generalizatio…

Node Classification

An Information-Theoretic Framework for Out-of-Distribution Generalization with Applications to Stochastic Gradient Langevin Dynamics

2024-03-29 · Wenliang Liu, Guanding Yu, Lele Wang, Renjie Liao

We study the Out-of-Distribution (OOD) generalization in machine learning and propose a general framework that establishes information-theoretic generalization bounds. Our framework interpolates freely between Integral P…

Generalization BoundsOut-of-Distribution Generalization

Instance-dependent $\ell_\infty$-bounds for policy evaluation in tabular reinforcement learning

2019-09-19 · Ashwin Pananjady, Martin J. Wainwright

Markov reward processes (MRPs) are used to model stochastic phenomena arising in operations research, control engineering, robotics, and artificial intelligence, as well as communication and transportation networks. In m…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)