English
Related papers

Related papers: Sharpness of Minima in Deep Matrix Factorization

200 papers

We study the learning performance of gradient descent when the empirical risk is weakly convex, namely, the smallest negative eigenvalue of the empirical risk's Hessian is bounded in magnitude. By showing that this eigenvalue can control…

Machine Learning · Statistics 2021-06-02 Dominic Richards , Mike Rabbat

Sharpness-Aware Minimization (SAM) has attracted considerable attention for its effectiveness in improving generalization in deep neural network training by explicitly minimizing sharpness in the loss landscape. Its success, however, relies…

Machine Learning · Computer Science 2025-06-16 Sungbin Shin , Dongyeop Lee , Maksym Andriushchenko , Namhoon Lee

When training neural networks with full-batch gradient descent (GD) and step size $\eta$, the largest eigenvalue of the Hessian -- the sharpness $S(\boldsymbol{\theta})$ -- rises to $2/\eta$ and hovers there, a phenomenon termed the Edge of…

Machine Learning · Computer Science 2026-04-24 Fangshuo Liao , Afroditi Kolomvaki , Anastasios Kyrillidis

We systematize the approach to the investigation of deep neural network landscapes by basing it on the geometry of the space of implemented functions rather than the space of parameters. Grouping classifiers into equivalence classes, we…

The success of deep learning has revealed the application potential of neural networks across the sciences and opened up fundamental theoretical problems. In particular, the fact that learning algorithms based on simple variants of gradient…

Disordered Systems and Neural Networks · Physics 2022-02-15 Carlo Baldassi , Clarissa Lauditi , Enrico M. Malatesta , Gabriele Perugini , Riccardo Zecchina

Neural networks trained with standard objectives exhibit behaviors characteristic of probabilistic inference: soft clustering, prototype specialization, and Bayesian uncertainty tracking. These phenomena appear across architectures -- in…

Machine Learning · Computer Science 2026-01-01 Alan Oursland

We study the optimization landscape of deep linear neural networks with the square loss. It is known that, under weak assumptions, there are no spurious local minima and no local maxima. However, the existence and diversity of non-strict…

Statistics Theory · Mathematics 2024-09-26 El Mehdi Achour , François Malgouyres , Sébastien Gerchinovitz

We propose a novel white-box approach to hyper-parameter optimization. Motivated by recent work establishing a relationship between flat minima and generalization, we first establish a relationship between the strong convexity of the loss…

Machine Learning · Computer Science 2024-02-08 Rahul Yedida , Snehanshu Saha

The Fisher information matrix (FIM) plays an essential role in statistics and machine learning as a Riemannian metric tensor or a component of the Hessian matrix of loss functions. Focusing on the FIM and its variants in deep neural…

Machine Learning · Statistics 2020-09-29 Ryo Karakida , Shotaro Akaho , Shun-ichi Amari

Nonconvex minimization algorithms often benefit from the use of second-order information as represented by the Hessian matrix. When the Hessian at a critical point possesses negative eigenvalues, the corresponding eigenvectors can be used…

Optimization and Control · Mathematics 2023-06-22 Warren Hare , Clément W. Royer

We give a simple local Polyak-Lojasiewicz (PL) criterion that guarantees linear (exponential) convergence of gradient flow and gradient descent to a zero-loss solution of a nonnegative objective. We then verify this criterion for the…

Machine Learning · Computer Science 2026-02-23 Sourav Chatterjee

In this paper, we present a local geometric analysis to interpret how deep feedforward neural networks extract low-dimensional features from high-dimensional data. Our study shows that, in a local geometric region, the optimal weight in one…

Machine Learning · Computer Science 2022-02-11 Md Kamran Chowdhury Shisher , Tasmeen Zaman Ornee , Yin Sun

We study gradient flow on the exponential loss for a classification problem with a one-layer softmax attention model, where the key and query weight matrices are trained separately. Under a separability assumption on the data, we show that…

Machine Learning · Computer Science 2024-03-14 Heejune Sheen , Siyu Chen , Tianhao Wang , Harrison H. Zhou

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…

Machine Learning · Computer Science 2021-10-19 Yossi Arjevani , Michael Field

We consider the problem of recovering low-rank matrices from random rank-one measurements, which spans numerous applications including covariance sketching, phase retrieval, quantum state tomography, and learning shallow polynomial neural…

Information Theory · Computer Science 2018-12-04 Yuanxin Li , Cong Ma , Yuxin Chen , Yuejie Chi

We propose a general theory for studying the \xl{landscape} of nonconvex \xl{optimization} with underlying symmetric structures \tz{for a class of machine learning problems (e.g., low-rank matrix factorization, phase retrieval, and deep…

Machine Learning · Computer Science 2018-01-23 Xingguo Li , Junwei Lu , Raman Arora , Jarvis Haupt , Han Liu , Zhaoran Wang , Tuo Zhao

Normalization methods play an important role in enhancing the performance of deep learning while their theoretical understandings have been limited. To theoretically elucidate the effectiveness of normalization, we quantify the geometry of…

Machine Learning · Statistics 2019-10-29 Ryo Karakida , Shotaro Akaho , Shun-ichi Amari

The paper surveys recent progresses in understanding the dynamics and loss landscape of the gradient flow equations associated to deep linear neural networks, i.e., the gradient descent training dynamics (in the limit when the step size…

Machine Learning · Computer Science 2025-11-14 Joel Wendin , Claudio Altafini

Gradient descent is commonly used to find minima in rough landscapes, particularly in recent machine learning applications. However, a theoretical understanding of why good solutions are found remains elusive, especially in strongly…

Machine Learning · Computer Science 2025-07-25 Tony Bonnaire , Giulio Biroli , Chiara Cammarota

Factorization-based gradient descent is a scalable and efficient algorithm for solving low-rank matrix completion. Recent progress in structured non-convex optimization has offered global convergence guarantees for gradient descent under…

Optimization and Control · Mathematics 2021-02-09 Trung Vu , Raviv Raich
‹ Prev 1 4 5 6 7 8 10 Next ›