English
Related papers

Related papers: Interpretable global minima of deep ReLU neural ne…

200 papers

Flat regions of the neural network loss landscape have long been hypothesized to correlate with better generalization properties. A closely related but distinct problem is training models that are robust to internal perturbations to their…

Machine Learning · Computer Science 2026-02-10 Philip Jacobson , Ben Feinberg , Suhas Kumar , Sapan Agarwal , T. Patrick Xiao , Christopher Bennett

Deploying deep learning models, comprising of non-linear combination of millions, even billions, of parameters is challenging given the memory, power and compute constraints of the real world. This situation has led to research into model…

Machine Learning · Computer Science 2020-05-29 Muhammad A. Shah , Raphael Olivier , Bhiksha Raj

In this work, we study the nonlinear dynamics of a shallow neural network trained with mean-squared loss and leaky ReLU activation. Under Gaussian inputs and equal layer width k, (1) we establish, based on the equivariant gradient degree, a…

Optimization and Control · Mathematics 2025-10-30 Jingzhou Liu

We develop an analytical framework to characterize the set of optimal ReLU neural networks by reformulating the non-convex training problem as a convex program. We show that the global optima of the convex parameterization are given by a…

Machine Learning · Computer Science 2024-01-22 Aaron Mishkin , Mert Pilanci

The success of deep neural networks is in part due to the use of normalization layers. Normalization layers like Batch Normalization, Layer Normalization and Weight Normalization are ubiquitous in practice, as they improve generalization…

Machine Learning · Computer Science 2020-06-15 Yonatan Dukler , Quanquan Gu , Guido Montúfar

We study the training of finite-width two-layer smoothed ReLU networks for binary classification using the logistic loss. We show that gradient descent drives the training loss to zero if the initial loss is small enough. When the data…

Machine Learning · Statistics 2021-07-02 Niladri S. Chatterji , Philip M. Long , Peter L. Bartlett

When training deep neural networks for classification tasks, an intriguing empirical phenomenon has been widely observed in the last-layer classifiers and features, where (i) the class means and the last-layer classifiers all collapse to…

Machine Learning · Computer Science 2022-03-15 Jinxin Zhou , Xiao Li , Tianyu Ding , Chong You , Qing Qu , Zhihui Zhu

This paper presents a new mathematical framework to analyze the loss functions of deep neural networks with ReLU functions. Furthermore, as as application of this theory, we prove that the loss functions can reconstruct the inputs of the…

Machine Learning · Statistics 2018-05-21 Akiyoshi Sannai

The Recurrent Neural Networks and their variants have shown promising performances in sequence modeling tasks such as Natural Language Processing. These models, however, turn out to be impractical and difficult to train when exposed to very…

Computer Vision and Pattern Recognition · Computer Science 2017-07-07 Yinchong Yang , Denis Krompass , Volker Tresp

We present a theoretically grounded approach to train deep neural networks, including recurrent networks, subject to class-dependent label noise. We propose two procedures for loss correction that are agnostic to both application domain and…

Machine Learning · Statistics 2017-03-23 Giorgio Patrini , Alessandro Rozza , Aditya Menon , Richard Nock , Lizhen Qu

Training neural network models with discrete (categorical or structured) latent variables can be computationally challenging, due to the need for marginalization over large or combinatorial sets. To circumvent this issue, one typically…

Machine Learning · Computer Science 2020-12-29 Gonçalo M. Correia , Vlad Niculae , Wilker Aziz , André F. T. Martins

Neural networks in general, from MLPs and CNNs to attention-based Transformers, are constructed from layers of linear combinations followed by nonlinear operations such as ReLU, Sigmoid, or Softmax. Despite their strength, these…

Machine Learning · Computer Science 2025-10-09 Weiguo Lu , Gangnan Yuan , Hong-kun Zhang , Shangyang Li

We give the first dimension-efficient algorithms for learning Rectified Linear Units (ReLUs), which are functions of the form $\mathbf{x} \mapsto \max(0, \mathbf{w} \cdot \mathbf{x})$ with $\mathbf{w} \in \mathbb{S}^{n-1}$. Our algorithm…

Machine Learning · Computer Science 2016-12-06 Surbhi Goel , Varun Kanade , Adam Klivans , Justin Thaler

An old idea in optimization theory says that since the gradient is a dual vector it may not be subtracted from the weights without first being mapped to the primal space where the weights reside. We take this idea seriously in this paper…

Machine Learning · Computer Science 2024-12-09 Jeremy Bernstein , Laker Newhouse

We investigate the loss surface of neural networks. We prove that even for one-hidden-layer networks with "slightest" nonlinearity, the empirical risks have spurious local minima in most cases. Our results thus indicate that in general "no…

Machine Learning · Computer Science 2019-05-29 Chulhee Yun , Suvrit Sra , Ali Jadbabaie

Most of the weights in a Lightweight Neural Network have a value of zero, while the remaining ones are either +1 or -1. These universal approximators require approximately 1.1 bits/weight of storage, posses a quick forward pass and achieve…

Machine Learning · Computer Science 2017-12-18 Altaf H. Khan

Supervised classification techniques use training samples to learn a classification rule with small expected 0-1 loss (error probability). Conventional methods enable tractable learning and provide out-of-sample generalization by using…

Machine Learning · Statistics 2023-08-21 Santiago Mazuelas , Mauricio Romero , Peter Grünwald

There is a growing demand for efficient data removal to comply with regulations like the GDPR and to mitigate the influence of biased or corrupted data. This has motivated the field of machine unlearning, which aims to eliminate the…

Machine Learning · Statistics 2026-04-08 Jingyi Xie , Linjun Zhang , Sai Li

This paper investigates efficient deep neural networks (DNNs) to replace dense unstructured weight matrices with structured ones that possess desired properties. The challenge arises because the optimal weight matrix structure in popular…

Machine Learning · Computer Science 2024-03-11 Changwoo Lee , Hun-Seok Kim

We propose a globally convergent multilevel training method for deep residual networks (ResNets). The devised method can be seen as a novel variant of the recursive multilevel trust-region (RMTR) method, which operates in hybrid…

Machine Learning · Computer Science 2022-06-14 Alena Kopaničáková , Rolf Krause
‹ Prev 1 8 9 10 Next ›