paper-with-me

홈 › Papers

A rescaling-invariant Lipschitz bound based on path-metrics for modern ReLU network parameterizations

2024-05-23 · Antoine Gonon, Nicolas Brisebarre, Elisa Riccietti, Rémi Gribonval

Lipschitz bounds on neural network parameterizations are important to establish generalization, quantization or pruning guarantees, as they control the robustness of the network with respect to parameter changes. Yet, there are few Lipschitz bounds with respect to parameters in the literature, and existing ones only apply to simple feedforward architectures, while also failing to capture the intrinsic rescaling-symmetries of ReLU networks. This paper proves a new Lipschitz bound in terms of the so-called path-metrics of the parameters. Since this bound is intrinsically invariant with respect to the rescaling symmetries of the networks, it sharpens previously known Lipschitz bounds. It is also, to the best of our knowledge, the first bound of its kind that is broadly applicable to modern networks such as ResNets, VGGs, U-nets, and many more.

📄 PDF Abstract BibTeX arXiv:2405.15006

Code (0)

등록된 구현이 없습니다.

Tasks

Generalization BoundsNetwork PruningQuantization

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Non-Vacuous Generalization Bounds: Can Rescaling Invariances Help?

2025-09-30 · Damien Rouchouse, Antoine Gonon, Rémi Gribonval, Benjamin Guedj arxiv

A central challenge in understanding generalization is to obtain non-vacuous guarantees that go beyond worst-case complexity over data or weight space. Among existing approaches, PAC-Bayes bounds stand out as they can pr…

Unit-Consistent (UC) Adjoint for GSD and Backprop in Deep Learning Applications

2026-01-15 · Jeffrey Uhlmann arxiv

Deep neural networks constructed from linear maps and positively homogeneous nonlinearities (e.g., ReLU) possess a fundamental gauge symmetry: the network function is invariant to node-wise diagonal rescalings. However, …

Path-SGD: Path-Normalized Optimization in Deep Neural Networks

2015-06-08 · NeurIPS 2015 12 · Behnam Neyshabur, Ruslan Salakhutdinov, Nathan Srebro

We revisit the choice of SGD for training deep neural networks by reconsidering the appropriate geometry in which to optimize the weights. We argue for a geometry invariant to rescaling of weights that does not affect th…

Toward bilipshiz geometric models

2025-11-13 · Yonatan Sverdlov, Eitan Rosen, Nadav Dym arxiv

Many neural networks for point clouds are, by design, invariant to the symmetries of this datatype: permutations and rigid motions. The purpose of this paper is to examine whether such networks preserve natural symmetry …

Point Clouds

Scale-Invariant Fast Convergence in Games

2026-02-12 · Taira Tsuchiya, Haipeng Luo, Shinji Ito arxiv

Scale-invariance in games has recently emerged as a widely valued desirable property. Yet, almost all fast convergence guarantees in learning in games require prior knowledge of the utility scale. To address this, we dev…