English
Related papers

Related papers: Sharpness of Minima in Deep Matrix Factorization

200 papers

Network pruning is a commonly used measure to alleviate the storage and computational burden of deep neural networks. However, the fundamental limit of network pruning is still lacking. To close the gap, in this work we'll take a…

Machine Learning · Statistics 2025-10-20 Qiaozhe Zhang , Ruijie Zhang , Jun Sun , Yingzhuang Liu

Stochastic Gradient Descent (SGD) and its variants are mainstream methods for training deep networks in practice. SGD is known to find a flat minimum that often generalizes well. However, it is mathematically unclear how deep learning can…

Machine Learning · Computer Science 2021-01-18 Zeke Xie , Issei Sato , Masashi Sugiyama

Matrix factorization models have been extensively studied as a valuable test-bed for understanding the implicit biases of overparameterized models. Although both low nuclear norm and low rank regularization have been studied for these…

Machine Learning · Computer Science 2025-06-03 Zhiwei Bai , Jiajie Zhao , Yaoyu Zhang

In this paper, we study the sharpness of a deep learning (DL) loss landscape around local minima in order to reveal systematic mechanisms underlying the generalization abilities of DL models. Our analysis is performed across varying network…

Machine Learning · Computer Science 2022-02-07 Devansh Bisla , Jing Wang , Anna Choromanska

Modern deep neural networks (DNNs) have achieved state-of-the-art performances but are typically over-parameterized. The over-parameterization may result in undesirably large generalization error in the absence of other customized training…

Machine Learning · Computer Science 2023-03-03 Jiawei Du , Daquan Zhou , Jiashi Feng , Vincent Y. F. Tan , Joey Tianyi Zhou

We present PYHESSIAN, a new scalable framework that enables fast computation of Hessian (i.e., second-order derivative) information for deep neural networks. PYHESSIAN enables fast computations of the top Hessian eigenvalues, the Hessian…

Machine Learning · Computer Science 2021-04-21 Zhewei Yao , Amir Gholami , Kurt Keutzer , Michael Mahoney

Sharpness-Aware Minimization (SAM) is a recent training method that relies on worst-case weight perturbations which significantly improves generalization in various settings. We argue that the existing justifications for the success of SAM…

Machine Learning · Computer Science 2022-06-14 Maksym Andriushchenko , Nicolas Flammarion

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…

Machine Learning · Computer Science 2020-07-21 Abbas Kazemipour , Brett W. Larsen , Shaul Druckmann

The geometrical features of the (non-convex) loss landscape of neural network models are crucial in ensuring successful optimization and, most importantly, the capability to generalize well. While minimizers' flatness consistently…

Disordered Systems and Neural Networks · Physics 2020-07-28 Carlo Baldassi , Riccardo Della Vecchia , Carlo Lucibello , Riccardo Zecchina

Modern neural networks are undeniably successful. Numerous studies have investigated how the curvature of loss landscapes can affect the quality of solutions. In this work we consider the Hessian matrix during network training. We reiterate…

Machine Learning · Computer Science 2023-05-31 Lawrence Wang , Stephen J. Roberts

Optimization methods play a crucial role in modern machine learning, powering the remarkable empirical achievements of deep learning models. These successes are even more remarkable given the complex non-convex nature of the loss landscape…

Machine Learning · Computer Science 2024-10-28 Rustem Islamov , Niccolò Ajroldi , Antonio Orvieto , Aurelien Lucchi

Training a neural network requires navigating a high-dimensional, non-convex loss surface to find parameters that minimize this loss. In many ways, it is surprising that optimizers such as stochastic gradient descent and ADAM can reliably…

Machine Learning · Computer Science 2026-02-06 Conor Rowan , Finn Murphy-Blanchard

When training deep neural networks with gradient descent, sharpness often increases -- a phenomenon known as progressive sharpening -- before saturating at the edge of stability. Although commonly observed in practice, the underlying…

Machine Learning · Computer Science 2025-06-10 Geonhui Yoo , Minhak Song , Chulhee Yun

Sparse matrix factorization is the problem of approximating a matrix $\mathbf{Z}$ by a product of $J$ sparse factors $\mathbf{X}^{(J)} \mathbf{X}^{(J-1)} \ldots \mathbf{X}^{(1)}$. This paper focuses on identifiability issues that appear in…

Machine Learning · Computer Science 2021-11-18 Léon Zheng , Elisa Riccietti , Rémi Gribonval

The notion of flat minima has played a key role in the generalization studies of deep learning models. However, existing definitions of the flatness are known to be sensitive to the rescaling of parameters. The issue suggests that the…

Machine Learning · Statistics 2019-01-29 Yusuke Tsuzuku , Issei Sato , Masashi Sugiyama

Traditional landscape analysis of deep neural networks aims to show that no sub-optimal local minima exist in some appropriate sense. From this, one may be tempted to conclude that descent algorithms which escape saddle points will reach a…

Machine Learning · Computer Science 2020-01-01 Shiyu Liang , Ruoyu Sun , R. Srikant

The key distinguishing property of a Bayesian approach is marginalization instead of optimization, not the prior, or Bayes rule. Bayesian inference is especially compelling for deep neural networks. (1) Neural networks are typically…

Machine Learning · Computer Science 2020-01-30 Andrew Gordon Wilson

Recent empirical advances show that training deep models with large learning rate often improves generalization performance. However, theoretical justifications on the benefits of large learning rate are highly limited, due to challenges in…

Machine Learning · Computer Science 2022-03-01 Yuqing Wang , Minshuo Chen , Tuo Zhao , Molei Tao

Matrix factorization is a popular approach for large-scale matrix completion. The optimization formulation based on matrix factorization can be solved very efficiently by standard algorithms in practice. However, due to the non-convexity…

Machine Learning · Computer Science 2016-11-18 Ruoyu Sun , Zhi-Quan Luo

This work finds the analytical expression of the global minima of a deep linear network with weight decay and stochastic neurons, a fundamental model for understanding the landscape of neural networks. Our result implies that the origin is…

Machine Learning · Statistics 2023-06-14 Liu Ziyin , Botao Li , Xiangming Meng