paper-with-me

Papers

Relative Flatness and Generalization

2020-01-03 · NeurIPS 2021 12 · Henning Petzka, Michael Kamp, Linara Adilova, Cristian Sminchisescu, Mario Boley

Flatness of the loss curve is conjectured to be connected to the generalization ability of machine learning models, in particular neural networks. While it has been empirically observed that flatness measures consistently correlate strongly with generalization, it is still an open theoretical problem why and under which circumstances flatness is connected to generalization, in particular in light of reparameterizations that change certain flatness measures but leave generalization unchanged. We investigate the connection between flatness and generalization by relating it to the interpolation from representative data, deriving notions of representativeness, and feature robustness. The notions allow us to rigorously connect flatness and generalization and to identify conditions under which the connection holds. Moreover, they give rise to a novel, but natural relative flatness measure that correlates strongly with generalization, simplifies to ridge regression for ordinary least squares, and solves the reparameterization issue.

📄 PDF Abstract BibTeX arXiv:2001.00939

Code (1)

kampmichael/RelativeFlatnessAndGeneralization 공식 구현 pytorch

Tasks

Generalization Bounds

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

FAM: Relative Flatness Aware Minimization

2023-07-05 · Linara Adilova, Amr Abourayya, Jianning Li, Amin Dada 외

Flatness of the loss curve around a model at hand has been shown to empirically correlate with its generalization ability. Optimizing for flatness has been proposed as early as 1994 by Hochreiter and Schmidthuber, and wa…

Flatness is Necessary, Neural Collapse is Not: Rethinking Generalization via Grokking

2025-09-22 · Ting Han, Linara Adilova, Henning Petzka, Jens Kleesiek 외 arxiv

Neural collapse, i.e., the emergence of highly symmetric, class-wise clustered representations, is frequently observed in deep networks and is often assumed to reflect or enable generalization. In parallel, flatness of t…

The Uncanny Valley: Exploring Adversarial Robustness from a Flatness Perspective

2024-05-27 · Nils Philipp Walter, Linara Adilova, Jilles Vreeken, Michael Kamp

Flatness of the loss surface not only correlates positively with generalization but is also related to adversarial robustness, since perturbations of inputs relate non-linearly to perturbations of weights. In this paper,…

Adversarial Robustness

An accurate flatness measure to estimate the generalization performance of CNN models

2026-03-09 · Rahman Taleghani, Maryam Mohammadi, Francesco Marchetti arxiv

Flatness measures based on the spectrum or the trace of the Hessian of the loss are widely used as proxies for the generalization ability of deep networks. However, most existing definitions are either tailored to fully …

Why flatness does and does not correlate with generalization for deep neural networks

2021-03-10 · Shuofeng Zhang, Isaac Reid, Guillermo Valle Pérez, Ard Louis

The intuition that local flatness of the loss landscape is correlated with better generalization for deep neural networks (DNNs) has been explored for decades, spawning many different flatness measures. Recently, this li…

image-classificationImage Classification