English
Related papers

Related papers: Convergence of optimizers implies eigenvalues filt…

200 papers

The Adam optimizer is currently presumably the most popular optimization method in deep learning. In this article we develop an ODE based method to study the Adam optimizer in a fast-slow scaling regime. For fixed momentum parameters and…

Optimization and Control · Mathematics 2025-11-07 Steffen Dereich , Arnulf Jentzen , Sebastian Kassing

We present a new family of min-max optimization algorithms that automatically exploit the geometry of the gradient data observed at earlier iterations to perform more informative extra-gradient steps in later ones. Thanks to this adaptation…

Optimization and Control · Mathematics 2020-11-20 Kimon Antonakopoulos , E. Veronica Belmega , Panayotis Mertikopoulos

We study the training dynamics of gradient descent in a softmax self-attention layer trained to perform linear regression and show that a simple first-order optimization algorithm can converge to the globally optimal self-attention…

Machine Learning · Computer Science 2026-03-03 Gautam Goel , Mahdi Soltanolkotabi , Peter Bartlett

Gradient Descent (GD) is a powerful workhorse of modern machine learning thanks to its scalability and efficiency in high-dimensional spaces. Its ability to find local minimisers is only guaranteed for losses with Lipschitz gradients, where…

Machine Learning · Computer Science 2023-07-27 Lei Chen , Joan Bruna

A number of optimization approaches have been proposed for optimizing nonconvex objectives (e.g. deep learning models), such as batch gradient descent, stochastic gradient descent and stochastic variance reduced gradient descent. Theory…

Machine Learning · Computer Science 2019-05-15 Jia Bi , Steve R. Gunn

A crucial component of machine learning algorithms is minimizing loss functions with less computational cost and less oscillations. While adaptive learning rate-based optimizers have been widely used for real-world tasks, they do not…

Machine Learning · Computer Science 2026-05-29 Sakshi Kumari , Shyam Kumar M , Sushmitha P

The properties of flat minima in the empirical risk landscape of neural networks have been debated for some time. Increasing evidence suggests they possess better generalization capabilities with respect to sharp ones. First, we discuss…

In this work, we first consider distributed convex constrained optimization problems where the objective function is encoded by multiple local and possibly nonsmooth objectives privately held by a group of agents, and propose a distributed…

Optimization and Control · Mathematics 2020-02-20 Changxin Liu , Huiping Li , Yang Shi

First-order optimization methods tend to inherently favor certain solutions over others when minimizing an underdetermined training objective that has multiple global optima. This phenomenon, known as implicit bias, plays a critical role in…

Machine Learning · Computer Science 2024-04-09 Guanghui Wang , Zihao Hu , Claudio Gentile , Vidya Muthukumar , Jacob Abernethy

Recent advances in convex optimization have leveraged computer-assisted proofs to develop optimized first-order methods that improve over classical algorithms. However, each optimized method is specially tailored for a particular problem…

Optimization and Control · Mathematics 2025-07-01 Jinho Bok , Jason M. Altschuler

Traditional analyses of gradient descent show that when the largest eigenvalue of the Hessian, also known as the sharpness $S(\theta)$, is bounded by $2/\eta$, training is "stable" and the training loss decreases monotonically. Recent…

Machine Learning · Computer Science 2023-04-12 Alex Damian , Eshaan Nichani , Jason D. Lee

Local optimization presents a promising approach to expensive, high-dimensional black-box optimization by sidestepping the need to globally explore the search space. For objective functions whose gradient cannot be evaluated directly,…

Machine Learning · Computer Science 2023-01-18 Quan Nguyen , Kaiwen Wu , Jacob R. Gardner , Roman Garnett

One of the mysteries in the success of neural networks is randomly initialized first order methods like gradient descent can achieve zero training loss even though the objective function is non-convex and non-smooth. This paper demystifies…

Machine Learning · Computer Science 2019-02-06 Simon S. Du , Xiyu Zhai , Barnabas Poczos , Aarti Singh

We describe an approximate dynamic programming approach to compute lower bounds on the optimal value function for a discrete time, continuous space, infinite horizon setting. The approach iteratively constructs a family of lower bounding…

Systems and Control · Electrical Eng. & Systems 2024-12-20 Paul N. Beuchat , Joseph Warrington , John Lygeros

Understanding the implicit bias of optimization algorithms is key to explaining and improving the generalization of deep models. The hyperbolic implicit bias induced by pointwise overparameterization promotes sparsity, but also yields a…

Machine Learning · Computer Science 2026-03-03 Tom Jacobs , Advait Gadhikar , Celia Rubio-Madrigal , Rebekka Burkholz

When equipped with efficient optimization algorithms, the over-parameterized neural networks have demonstrated high level of performance even though the loss function is non-convex and non-smooth. While many works have been focusing on…

Machine Learning · Computer Science 2021-03-11 Zhiqi Bu , Shiyun Xu , Kan Chen

In this paper, a general stochastic optimization procedure is studied, unifying several variants of the stochastic gradient descent such as, among others, the stochastic heavy ball method, the Stochastic Nesterov Accelerated Gradient…

Optimization and Control · Mathematics 2021-07-13 A. Barakat , P. Bianchi , W. Hachem , Sh. Schechtman

Bilevel optimization problems are receiving increasing attention in machine learning as they provide a natural framework for hyperparameter optimization and meta-learning. A key step to tackle these problems is the efficient computation of…

Machine Learning · Statistics 2025-05-20 Riccardo Grazzi , Massimiliano Pontil , Saverio Salzo

We develop a novel framework to study smooth and strongly convex optimization algorithms, both deterministic and stochastic. Focusing on quadratic functions we are able to examine optimization algorithms as a recursive application of linear…

Optimization and Control · Mathematics 2015-03-25 Yossi Arjevani , Shai Shalev-Shwartz , Ohad Shamir

We present a subgradient method for minimizing non-smooth, non-Lipschitz convex optimization problems. The only structure assumed is that a strictly feasible point is known. We extend the work of Renegar [5] by taking a different…

Optimization and Control · Mathematics 2018-02-28 Benjamin Grimmer