English
Related papers

Related papers: Neural Collapse with Cross-Entropy Loss

200 papers

We study the error landscape of deep linear and nonlinear neural networks with the squared error loss. Minimizing the loss of a deep linear neural network is a nonconvex problem, and despite recent progress, our understanding of this loss…

Machine Learning · Computer Science 2018-03-28 Chulhee Yun , Suvrit Sra , Ali Jadbabaie

For an $n$-element subset $U$ of $\mathbb{Z}^2$, select $x$ from $U$ according to harmonic measure from infinity, remove $x$ from $U$, and start a random walk from $x$. If the walk leaves from $y$ when it first enters $U$, add $y$ to $U$.…

Probability · Mathematics 2021-10-27 Jacob Calvert , Shirshendu Ganguly , Alan Hammond

We study the implicit bias of flatness / low (loss) curvature and its effects on generalization in two-layer overparameterized ReLU networks with multivariate inputs -- a problem well motivated by the minima stability and edge-of-stability…

Machine Learning · Statistics 2026-01-13 Tongtong Liang , Dan Qiao , Yu-Xiang Wang , Rahul Parhi

We analyze single-layer neural networks with the Xavier initialization in the asymptotic regime of large numbers of hidden units and large numbers of stochastic gradient descent training steps. The evolution of the neural network during…

Probability · Mathematics 2022-04-13 Justin Sirignano , Konstantinos Spiliopoulos

In quantum mechanics (formulated, say, in Schr\"{o}dinger picture) only the knowledge of a complete set of observables $\Lambda_j$ enables us to declare the related physical inner product (i.e., the Hilbert-space metric $\Theta$ such that…

Quantum Physics · Physics 2024-03-15 Miloslav Znojil

Loss reweighting is a widely used strategy for long-tailed classification, but existing reweighting strategies often rely on heuristics and rarely define a well-specified target. Inspired by Neural Collapse (NC), the ideal simplex…

Machine Learning · Computer Science 2026-05-12 Jinping Wang , Zixin Tong , Zhiwu Xie , Zhiqiang Gao

Recent advances in theoretical Deep Learning have introduced geometric properties that occur during training, past the Interpolation Threshold -- where the training error reaches zero. We inquire into the phenomena coined Neural Collapse in…

Machine Learning · Computer Science 2022-06-14 Ido Ben-Shaul , Shai Dekel

A recent analysis of a model of iterative neural network in Hilbert spaces established fundamental properties of such networks, such as existence of the fixed points sets, convergence analysis, and Lipschitz continuity. Building on these…

Machine Learning · Computer Science 2019-08-20 Tomasz Piotrowski , Krzysztof Rykaczewski

Among many mysteries behind the success of deep networks lies the exceptional discriminative power of their learned representations as manifested by the intriguing Neural Collapse (NC) phenomenon, where simple feature structures emerge at…

Machine Learning · Computer Science 2025-10-27 Hancheng Min , Zhihui Zhu , René Vidal

This thesis is divided in two parts, each one addressing problems that can be relevant in the study of compact objects. The first part deals with the study of a magnetized and self-gravitating gas of degenerated fermions (electrons and…

High Energy Physics - Theory · Physics 2011-03-10 A. Ulacia Rey

We characterize the exact solutions to neural network descrambling--a mathematical model for explaining the fully connected layers of trained neural networks (NNs). By reformulating the problem to the minimization of the Brockett function…

Machine Learning · Computer Science 2024-09-04 Shashank Sule , Richard G. Spencer , Wojciech Czaja

Existing graph convolutional networks focus on the neighborhood aggregation scheme. When applied to semi-supervised learning, they often suffer from the overfitting problem as the networks are trained with the cross-entropy loss on a small…

Machine Learning · Computer Science 2020-02-18 Qilin Li , Wanquan Liu , Ling Li

Motivated by empirical observations of prolonged plateaus and stage-wise progression during training, we investigate the loss landscape of transformer models trained on in-context next-token prediction tasks. In particular, we focus on…

Machine Learning · Computer Science 2025-08-20 Aditya Varre , Gizem Yüce , Nicolas Flammarion

We study the existence and uniqueness of solutions to the inverse quasi-variational inequality problem. Motivated by the neural network approach to solving optimization problems such as variational inequality, monotone inclusion, and…

Optimization and Control · Mathematics 2022-04-13 Soumitra Dey , Simeon Reich

A quadratic approximation of neural network loss landscapes has been extensively used to study the optimization process of these networks. Though, it usually holds in a very small neighborhood of the minimum, it cannot explain many…

Machine Learning · Computer Science 2022-06-23 Chao Ma , Daniel Kunin , Lei Wu , Lexing Ying

We explore the universality of neural encodings in convolutional neural networks trained on image classification tasks. We develop a procedure to directly compare the learned weights rather than their representations. It is based on a…

Machine Learning · Computer Science 2024-10-01 Florentin Guth , Brice Ménard

We study norm-based uniform convergence bounds for neural networks, aiming at a tight understanding of how these are affected by the architecture and type of norm constraint, for the simple class of scalar-valued one-hidden-layer networks,…

Machine Learning · Computer Science 2022-09-23 Gal Vardi , Ohad Shamir , Nathan Srebro

Recently, substantial research efforts in Deep Metric Learning (DML) focused on designing complex pairwise-distance losses, which require convoluted schemes to ease optimization, such as sample mining or pair weighting. The standard…

Machine Learning · Computer Science 2021-11-29 Malik Boudiaf , Jérôme Rony , Imtiaz Masud Ziko , Eric Granger , Marco Pedersoli , Pablo Piantanida , Ismail Ben Ayed

We develop a geometric theory of projection heads in self-supervised learning by modeling the head as a trainable Riemannian metric on the backbone representation manifold. We show that linear heads perform implicit subspace whitening,…

Machine Learning · Computer Science 2026-05-19 Faris Chaudhry

This paper introduces a new technique to measure the feature dependency of neural network models. The motivation is to better understand a model by querying whether it is using information from human-understandable features, e.g.,…

Machine Learning · Computer Science 2024-10-10 Yinzhu Jin , Matthew B. Dwyer , P. Thomas Fletcher