paper-with-me

Papers

Do highly over-parameterized neural networks generalize since bad solutions are rare?

2022-11-07 · Julius Martinetz, Thomas Martinetz

We study over-parameterized classifiers where Empirical Risk Minimization (ERM) for learning leads to zero training error. In these over-parameterized settings there are many global minima with zero training error, some of which generalize better than others. We show that under certain conditions the fraction of "bad" global minima with a true error larger than {\epsilon} decays to zero exponentially fast with the number of training data n. The bound depends on the distribution of the true error over the set of classifier functions used for the given classification problem, and does not necessarily depend on the size or complexity (e.g. the number of parameters) of the classifier function set. This insight may provide a novel perspective on the unexpectedly good generalization even of highly over-parameterized neural networks. We substantiate our theoretical findings through experiments on synthetic data and a subset of MNIST. Additionally, we assess our hypothesis using VGG19 and ResNet18 on a subset of Caltech101.

📄 PDF Abstract BibTeX arXiv:2211.03570

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

Learning Low Dimensional State Spaces with Overparameterized Recurrent Neural Nets

2022-10-25 · Edo Cohen-Karlik, Itamar Menuhin-Gruman, Raja Giryes, Nadav Cohen 외

Overparameterization in deep learning typically refers to settings where a trained neural network (NN) has representational capacity to fit the training data in many ways, some of which generalize well, while others do n…

The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks

2023-03-02 · NeurIPS 2023 11

In this work, we study the implications of the implicit bias of gradient flow on generalization and adversarial robustness in ReLU networks. We focus on a setting where the data consists of clusters and the correlations …

Adversarial Robustness

The Low-Rank Simplicity Bias in Deep Networks

2021-03-18 · Minyoung Huh, Hossein Mobahi, Richard Zhang, Brian Cheung 외

Modern deep neural networks are highly over-parameterized compared to the data on which they are trained, yet they often generalize remarkably well. A flurry of recent work has asked: why do deep networks not overfit to …

Image Classification

Classification vs regression in overparameterized regimes: Does the loss function matter?

2020-05-16 · Vidya Muthukumar, Adhyyan Narang, Vignesh Subramanian, Mikhail Belkin 외

We compare classification and regression tasks in an overparameterized linear model with Gaussian features. On the one hand, we show that with sufficient overparameterization all training points are support vectors: solu…

General Classificationregression

How noise affects the Hessian spectrum in overparameterized neural networks

2019-10-01 · Mingwei Wei, David J. Schwab

Stochastic gradient descent (SGD) forms the core optimization method for deep neural networks. While some theoretical progress has been made, it still remains unclear why SGD leads the learning dynamics in overparameteri…