paper-with-me

Papers

A PAC-Bayesian Generalization Bound for Equivariant Networks

2022-10-24 · Arash Behboodi, Gabriele Cesa, Taco Cohen

Equivariant networks capture the inductive bias about the symmetry of the learning task by building those symmetries into the model. In this paper, we study how equivariance relates to generalization error utilizing PAC Bayesian analysis for equivariant networks, where the transformation laws of feature spaces are determined by group representations. By using perturbation analysis of equivariant networks in Fourier domain for each layer, we derive norm-based PAC-Bayesian generalization bounds. The bound characterizes the impact of group size, and multiplicity and degree of irreducible representations on the generalization error and thereby provide a guideline for selecting them. In general, the bound indicates that using larger group size in the model improves the generalization error substantiated by extensive numerical experiments.

📄 PDF Abstract BibTeX arXiv:2210.13150

Code (0)

등록된 구현이 없습니다.

Tasks

Generalization BoundsInductive Bias

Similar Papers 제목 키워드 기반

A PAC-Bayesian approach to generalization for quantum models

2026-03-24 · Pablo Rodriguez-Grasa, Matthias C. Caro, Jens Eisert, Elies Gil-Fuster 외 arxiv

Generalization is a central concept in machine learning theory, yet for quantum models, it is predominantly analyzed through uniform bounds that depend on a model's overall capacity rather than the specific function lear…

Quantum Machine Learning

Generalization Bounds for Equivariant Networks on Markov Data

2025-03-01 · Hui Li, Zhiguo Wang, Bohui Chen, Li Sheng

Equivariant neural networks play a pivotal role in analyzing datasets with symmetry properties, particularly in complex data structures. However, integrating equivariance with Markov properties presents notable challenge…

Generalization Bounds

Improved Generalization Bounds of Group Invariant / Equivariant Deep Networks via Quotient Feature Spaces

2019-10-15 · Akiyoshi Sannai, Masaaki Imaizumi, Makoto Kawano

Numerous invariant (or equivariant) neural networks have succeeded in handling invariant data such as point clouds and graphs. However, a generalization theory for the neural networks has not been well developed, because…

Generalization Bounds

Data Augmentation vs. Equivariant Networks: A Theory of Generalization on Dynamics Forecasting

2022-06-19 · Rui Wang, Robin Walters, Rose Yu

Exploiting symmetry in dynamical systems is a powerful way to improve the generalization of deep learning. The model learns to be invariant to transformation and hence is more robust to distribution shift. Data augmentat…

Data AugmentationGeneralization Bounds

Equivariant score-based generative models provably learn distributions with symmetries efficiently

2024-10-02 · Ziyu Chen, Markos A. Katsoulakis, Benjamin J. Zhang

Symmetry is ubiquitous in many real-world phenomena and tasks, such as physics, images, and molecular simulations. Empirical studies have demonstrated that incorporating symmetries into generative models can provide bett…

Data AugmentationGeneralization BoundsInductive Bias