中文
相关论文

相关论文: Annihilation of Spurious Minima in Two-Layer ReLU …

200 篇论文

We study the optimization problem associated with fitting two-layer ReLU neural networks with respect to the squared loss, where labels are generated by a target network. We make use of the rich symmetry structure to develop a novel set of…

机器学习 · 计算机科学 2021-10-19 Yossi Arjevani , Michael Field

We consider the optimization problem associated with training simple ReLU neural networks of the form $\mathbf{x}\mapsto \sum_{i=1}^{k}\max\{0,\mathbf{w}_i^\top \mathbf{x}\}$ with respect to the squared loss. We provide a computer-assisted…

机器学习 · 计算机科学 2018-08-10 Itay Safran , Ohad Shamir

We consider the optimization problem associated with fitting two-layer ReLU networks with respect to the squared loss, where labels are assumed to be generated by a target network. Focusing first on standard Gaussian inputs, we show that…

机器学习 · 计算机科学 2023-12-29 Yossi Arjevani , Michael Field

We consider the optimization problem associated with fitting two-layer ReLU networks with $k$ hidden neurons, where labels are assumed to be generated by a (teacher) neural network. We leverage the rich symmetry exhibited by such models to…

机器学习 · 计算机科学 2021-09-22 Yossi Arjevani , Michael Field

We consider the optimization problem associated with training two-layer ReLU networks with \(d\) inputs under the squared loss, where the labels are generated by a target network. Recent work has identified two distinct classes of infinite…

机器学习 · 计算机科学 2026-01-21 Yossi Arjevani

We consider the optimization problem associated with fitting two-layers ReLU networks with respect to the squared loss, where labels are generated by a target network. We leverage the rich symmetry structure to analytically characterize the…

机器学习 · 计算机科学 2020-10-19 Yossi Arjevani , Michael Field

We study the population loss landscape of two-layer ReLU networks of the form $\sum_{k=1}^K \mathrm{ReLU}(w_k^\top x)$ in a realisable teacher-student setting with Gaussian covariates. We show that local minima admit an exact…

机器学习 · 统计学 2026-04-13 Jie Huang , Bruno Loureiro , Stefano Sarao Mannelli

The optimization of neural networks under weight decay remains poorly understood from a theoretical standpoint. While weight decay is standard practice in modern training procedures, most theoretical analyses focus on unregularized…

机器学习 · 计算机科学 2025-05-29 Etienne Boursier , Matthew Bowditch , Matthias Englert , Ranko Lazic

Despite their practical success, a theoretical understanding of the loss landscape of neural networks has proven challenging due to the high-dimensional, non-convex, and highly nonlinear structure of such models. In this paper, we…

机器学习 · 计算机科学 2020-07-21 Abbas Kazemipour , Brett W. Larsen , Shaul Druckmann

We study how permutation symmetries in overparameterized multi-layer neural networks generate `symmetry-induced' critical points. Assuming a network with $ L $ layers of minimal widths $ r_1^*, \ldots, r_{L-1}^* $ reaches a zero-loss…

We draw connections between simple neural networks and under-determined linear systems to comprehensively explore several interesting theoretical questions in the study of neural networks. First, we emphatically show that it is unsurprising…

数值分析 · 数学 2020-11-02 Austin R. Benson , Anil Damle , Alex Townsend

Overparameterization is central to the success of deep learning, yet the mechanisms by which it improves optimization remain incompletely understood. We analyze weight-space symmetries in neural networks and show that overparameterization…

机器学习 · 计算机科学 2026-05-11 Kusha Sareen , Mohammad Pedramfar , Sékou-Oumar Kaba , Mehran Shakerinava , Siamak Ravanbakhsh

We study the loss landscape of both shallow and deep, mildly overparameterized ReLU neural networks on a generic finite input dataset for the squared error loss. We show both by count and volume that most activation patterns correspond to…

机器学习 · 计算机科学 2024-02-09 Kedar Karhadkar , Michael Murray , Hanna Tseran , Guido Montúfar

We study the loss surface of neural networks equipped with a hinge loss criterion and ReLU or leaky ReLU nonlinearities. Any such network defines a piecewise multilinear form in parameter space. By appealing to harmonic analysis we show…

机器学习 · 计算机科学 2018-07-24 Thomas Laurent , James von Brecht

We study the effects of mild over-parameterization on the optimization landscape of a simple ReLU neural network of the form $\mathbf{x}\mapsto\sum_{i=1}^k\max\{0,\mathbf{w}_i^{\top}\mathbf{x}\}$, in a well-studied teacher-student setting…

机器学习 · 计算机科学 2021-08-02 Itay Safran , Gilad Yehudai , Ohad Shamir

We study the overparametrization bounds required for the global convergence of stochastic gradient descent algorithm for a class of one hidden layer feed-forward neural networks, considering most of the activation functions used in…

机器学习 · 计算机科学 2022-11-17 Bartłomiej Polaczyk , Jacek Cyranka

Understanding generalization of overparametrized neural networks remains a fundamental challenge in machine learning. Most of the literature mostly studies generalization from an interpolation point of view, taking convergence of parameters…

机器学习 · 计算机科学 2025-06-13 Etienne Boursier , Nicolas Flammarion

We study the topology of the loss landscape of one-hidden-layer ReLU networks under overparameterization. On the theory side, we (i) prove that for convex $L$-Lipschitz losses with an $\ell_1$-regularized second layer, every pair of models…

机器学习 · 计算机科学 2026-02-20 Saveliy Baturin

We theoretically study the landscape of the training error for neural networks in overparameterized cases. We consider three basic methods for embedding a network into a wider one with more hidden units, and discuss whether a minimum point…

机器学习 · 计算机科学 2019-06-17 Kenji Fukumizu , Shoichiro Yamaguchi , Yoh-ichi Mototake , Mirai Tanaka

Under mild assumptions, we investigate the geometry of the loss landscape for two-layer neural networks in the vicinity of global minima. Utilizing novel techniques, we demonstrate: (i) how global minima with zero generalization error…

机器学习 · 计算机科学 2025-04-11 Leyang Zhang , Yaoyu Zhang , Tao Luo
‹ 上一页 1 2 3 10 下一页 ›