English
Related papers

Related papers: How to Escape Saddle Points Efficiently

200 papers

We study the minimization of non-convex functionals over the Wasserstein space. While recent work has showed that perturbed Wasserstein gradient methods can avoid saddle points for benign landscapes, existing approaches remain essentially…

Optimization and Control · Mathematics 2026-05-19 Razvan-Andrei Lascu , Taiji Suzuki

The problem of saddle-point avoidance for non-convex optimization is quite challenging in large scale distributed learning frameworks, such as Federated Learning, especially in the presence of Byzantine workers. The celebrated…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-12-30 Avishek Ghosh , Raj Kumar Maity , Arya Mazumdar , Kannan Ramchandran

In this paper, we show that under over-parametrization several standard stochastic optimization algorithms escape saddle-points and converge to local-minimizers much faster. One of the fundamental aspects of over-parametrized models is that…

Machine Learning · Statistics 2020-09-29 Abhishek Roy , Krishnakumar Balasubramanian , Saeed Ghadimi , Prasant Mohapatra

Under appropriate cooperation protocols and parameter choices, fully decentralized solutions for stochastic optimization have been shown to match the performance of centralized solutions and result in linear speedup (in the number of…

Multiagent Systems · Computer Science 2019-10-31 Stefan Vlaski , Ali H. Sayed

We study the convergence properties of gradient descent for training deep linear neural networks, i.e., deep matrix factorizations, by extending a previous analysis for the related gradient flow. We show that under suitable conditions on…

Machine Learning · Computer Science 2021-11-25 Gabin Maxime Nguegnang , Holger Rauhut , Ulrich Terstiege

We propose an alternating subgradient method with non-constant step sizes for solving convex-concave saddle-point problems associated with general convex-concave functions. We assume that the sequence of our step sizes is not summable but…

Optimization and Control · Mathematics 2023-05-26 Hui Ouyang

We study generalized smoothness in nonconvex optimization, focusing on $(L_0, L_1)$-smoothness and anisotropic smoothness. The former was empirically derived from practical neural network training examples, while the latter arises naturally…

Optimization and Control · Mathematics 2025-09-22 Alexander Bodard , Panagiotis Patrinos

We consider the minimization of non-convex quadratic forms regularized by a cubic term, which exhibit multiple saddle points and poor local minima. Nonetheless, we prove that, under mild assumptions, gradient descent approximates the…

Optimization and Control · Mathematics 2022-08-31 Yair Carmon , John C. Duchi

Momentum Stochastic Gradient Descent (MSGD) algorithm has been widely applied to many nonconvex optimization problems in machine learning, e.g., training deep neural networks, variational Bayesian inference, and etc. Despite its empirical…

Machine Learning · Computer Science 2021-03-09 Tianyi Liu , Zhehui Chen , Enlu Zhou , Tuo Zhao

Distributed nonconvex optimization underpins key functionalities of numerous distributed systems, ranging from power systems, smart buildings, cooperative robots, vehicle networks to sensor networks. Recently, it has also merged as a…

Optimization and Control · Mathematics 2024-03-18 Yanan Bo , Yongqiang Wang

We study the generalization performance of gradient methods in the fundamental stochastic convex optimization setting, focusing on its dimension dependence. First, for full-batch gradient descent (GD) we give a construction of a learning…

Machine Learning · Computer Science 2024-01-23 Matan Schliserman , Uri Sherman , Tomer Koren

We analyze convergence of gradient-descent methods on Riemannian manifolds. In particular, we study randomization of Riemannian gradient algorithms for minimizing smooth cost functions (of Morse-Bott type). We prove that randomized gradient…

Optimization and Control · Mathematics 2025-07-08 Emanuel Malvetti , Christian Arenz , Gunther Dirr , Thomas Schulte-Herbrüggen

Many modern machine learning applications - from online principal component analysis to covariance matrix identification and dictionary learning - can be formulated as minimization problems on Riemannian manifolds, and are typically solved…

Optimization and Control · Mathematics 2023-11-07 Ya-Ping Hsieh , Mohammad Reza Karimi , Andreas Krause , Panayotis Mertikopoulos

It has been shown that gradient descent can yield the zero training loss in the over-parametrized regime (the width of the neural networks is much larger than the number of data points). In this work, combining the ideas of some existing…

Optimization and Control · Mathematics 2019-11-05 Lei Li

This paper focuses on solving a stochastic saddle point problem (SPP) under an overparameterized regime for the case, when the gradient computation is impractical. As an intermediate step, we generalize Same-sample Stochastic Extra-gradient…

Optimization and Control · Mathematics 2024-06-05 Ekaterina Statkevich , Sofiya Bondar , Darina Dvinskikh , Alexander Gasnikov , Aleksandr Lobanov

We consider the problem of finding local minimizers in non-convex and non-smooth optimization. Under the assumption of strict saddle points, positive results have been derived for first-order methods. We present the first known results for…

Machine Learning · Computer Science 2019-08-13 Zhishen Huang , Stephen Becker

Recent years have seen a growing interest in understanding deep neural networks from an optimization perspective. It is understood now that converging to low-cost local minima is sufficient for such models to become effective in practice.…

Machine Learning · Statistics 2017-06-08 Adepu Ravi Sankar , Vineeth N Balasubramanian

Gradient descent finds a global minimum in training deep neural networks despite the objective function being non-convex. The current paper proves gradient descent achieves zero training loss in polynomial time for a deep over-parameterized…

Machine Learning · Computer Science 2019-05-30 Simon S. Du , Jason D. Lee , Haochuan Li , Liwei Wang , Xiyu Zhai

Stochastic gradient descent (SGD) is a standard optimization method to minimize a training error with respect to network parameters in modern neural network learning. However, it typically suffers from proliferation of saddle points in the…

Machine Learning · Computer Science 2017-11-23 Haiping Huang , Taro Toyoizumi

Satisfaction of the strict saddle property has become a standard assumption in non-convex optimization, and it ensures that many first-order optimization algorithms will almost always escape saddle points. However, functions exist in…

Optimization and Control · Mathematics 2022-08-23 Matthew Ubl , Kasra Yazdani , Matthew T. Hale
‹ Prev 1 4 5 6 7 8 10 Next ›