English
Related papers

Related papers: On the Interplay Between Stepsize Tuning and Progr…

200 papers

We study the algorithmic stability of Nesterov's accelerated gradient method. For convex quadratic objectives, Chen et al. (2018) proved that the uniform stability of the method grows quadratically with the number of optimization steps, and…

Machine Learning · Computer Science 2021-06-22 Amit Attia , Tomer Koren

Very little is known about the training dynamics of adaptive gradient methods like Adam in deep learning. In this paper, we shed light on the behavior of these algorithms in the full-batch and sufficiently large batch settings.…

Gradient-based iterative optimization methods are the workhorse of modern machine learning. They crucially rely on careful tuning of parameters like learning rate and momentum. However, one typically sets them using heuristic approaches…

Machine Learning · Computer Science 2025-12-05 Dravyansh Sharma

The Hessian spectrum of trained deep networks exhibits a characteristic structure: a continuous bulk of near-zero eigenvalues and a small number of large outlier eigenvalues (spikes), confirming the relevance of Random Matrix Theory in deep…

Machine Learning · Computer Science 2026-05-19 Hugo Vigna , Samuel Bontemps

Approximate dynamic programming (ADP) has proven itself in a wide range of applications spanning large-scale transportation problems, health care, revenue management, and energy systems. The design of effective ADP algorithms has many…

Optimization and Control · Mathematics 2014-07-15 Ilya O. Ryzhov , Peter I. Frazier , Warren B. Powell

Recent works have shown that stochastic gradient descent (SGD) achieves the fast convergence rates of full-batch gradient descent for over-parameterized models satisfying certain interpolation conditions. However, the step-size used in…

Machine Learning · Computer Science 2021-06-07 Sharan Vaswani , Aaron Mishkin , Issam Laradji , Mark Schmidt , Gauthier Gidel , Simon Lacoste-Julien

Automated hyperparameter tuning aspires to facilitate the application of machine learning for non-experts. In the literature, different optimization approaches are applied for that purpose. This paper investigates the performance of…

Machine Learning · Computer Science 2019-04-16 Mischa Schmidt , Shahd Safarani , Julia Gastinger , Tobias Jacobs , Sebastien Nicolas , Anett Schülke

Recently, many machine learning optimizers have been analysed considering them as the asymptotic limit of some differential equations when the step size goes to zero. In other words, the optimizers can be seen as a finite difference scheme…

Numerical Analysis · Mathematics 2024-07-02 Bilel Bensaid , Gaël Poëtte , Rodolphe Turpault

In modern deep learning, weight decay is often credited with "stabilizing" training dynamics, diverging from its classical role as a static regularization penalty. We investigate a fundamental question: *does weight decay stabilize training…

Machine Learning · Computer Science 2026-05-19 Marius Saether , Amir Kolic , Tomaso Poggio , Pierfrancesco Beneventano

We propose an adaptive step-size rule for decentralized optimization. Choosing a step-size that balances convergence and stability is challenging. This is amplified in the decentralized setting as agents observe only local (possibly…

Optimization and Control · Mathematics 2026-02-17 Aaron Fainman , Stefan Vlaski

Classical analyses of gradient descent (GD) define a stability threshold based on the largest eigenvalue of the loss Hessian, often termed sharpness. When the learning rate lies below this threshold, training is stable and the loss…

Machine Learning · Computer Science 2025-11-18 Lawrence Wang , Stephen J. Roberts

We introduce a novel dynamic learning-rate scheduling scheme grounded in theory with the goal of simplifying the manual and time-consuming tuning of schedules in practice. Our approach is based on estimating the locally-optimal stepsize,…

Machine Learning · Computer Science 2023-11-27 Gilad Yehudai , Alon Cohen , Amit Daniely , Yoel Drori , Tomer Koren , Mariano Schain

The performance of modern reinforcement learning algorithms critically relies on tuning ever-increasing numbers of hyperparameters. Often, small changes in a hyperparameter can lead to drastic changes in performance, and different…

Machine Learning · Computer Science 2025-02-05 Jacob Adkins , Michael Bowling , Adam White

The pairwise objective paradigms are an important and essential aspect of machine learning. Examples of machine learning approaches that use pairwise objective functions include differential network in face recognition, metric learning,…

Machine Learning · Computer Science 2022-10-04 Hilal AlQuabeh , Aliakbar Abdurahimov

We propose a homogeneous multilayer perceptron parameterization with polynomial hidden layer width pattern and analyze its training dynamics under stochastic gradient descent with depthwise gradient scaling in a general supervised learning…

Machine Learning · Computer Science 2025-05-20 Dávid Terjék

Stochastic methods with coordinate-wise adaptive stepsize (such as RMSprop and Adam) have been widely used in training deep neural networks. Despite their fast convergence, they can generalize worse than stochastic gradient descent. In this…

Machine Learning · Computer Science 2019-05-27 Shuai Zheng , James T. Kwok

Deep learning (DL) creates impactful advances following a virtuous recipe: model architecture search, creating large training data sets, and scaling computation. It is widely believed that growing training sets and models should improve…

Novel technologies in automated machine learning ease the complexity of algorithm selection and hyperparameter optimization. Hyperparameters are important for machine learning models as they significantly influence the performance of…

Machine Learning · Computer Science 2021-08-31 Mohamadjavad Bahmani , Radwa El Shawi , Nshan Potikyan , Sherif Sakr

We investigate the convergence of stochastic mirror descent (SMD) under interpolation in relatively smooth and smooth convex optimization. In relatively smooth convex optimization we provide new convergence guarantees for SMD with a…

Optimization and Control · Mathematics 2023-05-26 Ryan D'Orazio , Nicolas Loizou , Issam Laradji , Ioannis Mitliagkas

Regularization has long been utilized to learn sparsity in deep neural network pruning. However, its role is mainly explored in the small penalty strength regime. In this work, we extend its application to a new scenario where the…

Computer Vision and Pattern Recognition · Computer Science 2021-04-07 Huan Wang , Can Qin , Yulun Zhang , Yun Fu