English
Related papers

Related papers: Adam Can Converge Without Any Modification On Upda…

200 papers

Nowadays, online learning is an appealing learning paradigm, which is of great interest in practice due to the recent emergence of large scale applications such as online advertising placement and online web ranking. Standard online…

Machine Learning · Computer Science 2019-11-27 Biyi Fang , Diego Klabjan

Atomistic foundation models constitute a paradigm shift in computational materials science by providing universal machine-learned interatomic potentials with broad transferability across chemical spaces. Although fine-tuning is essential…

Computational Physics · Physics 2025-12-08 Xiaoqing Liu , Yangshuai Wang , Teng Zhao

In this work, we offer a theoretical analysis of two modern optimization techniques for training large and complex models: (i) adaptive optimization algorithms, such as Adam, and (ii) the model exponential moving average (EMA).…

Machine Learning · Computer Science 2024-10-31 Kwangjun Ahn , Ashok Cutkosky

The dynamics of an agreement protocol interacting with a disagreement process over a common random network is considered. The model can represent the spreading of true and false information over a communication network, the propagation of…

Social and Information Networks · Computer Science 2012-08-17 Guodong Shi , Mikael Johansson , Karl Henrik Johansson

Adam is the go-to optimizer for training modern machine learning models, but it requires additional memory to maintain the moving averages of the gradients and their squares. While various low-memory optimizers have been proposed that…

Machine Learning · Computer Science 2025-03-19 Dayal Singh Kalra , John Kirchenbauer , Maissam Barkeshli , Tom Goldstein

In this paper, we prove that an Adam-type algorithm with smooth clipping approaches the global minimizer of the regularized non-convex loss function. Adding smooth clipping and taking the state space as the set of all trajectories, we can…

Machine Learning · Computer Science 2023-12-06 Keisuke Suzuki

While attractive from a theoretical perspective, finely stratified experiments such as paired designs suffer from certain analytical limitations not present in block-randomized experiments with multiple treated and control individuals in…

Methodology · Statistics 2017-06-21 Colin B. Fogarty

A very simple unidimensional function with Lipschitz continuous gradient is constructed such that the ADAM algorithm with constant stepsize, started from the origin, diverges when applied to minimize this function in the absence of noise on…

Machine Learning · Computer Science 2023-08-03 Ph. L. Toint

Regularisation theory in Banach spaces, and non--norm-squared regularisation even in finite dimensions, generally relies upon Bregman divergences to replace norm convergence. This is comparable to the extension of first-order optimisation…

Optimization and Control · Mathematics 2021-03-19 Tuomo Valkonen

Adam has been shown to outperform gradient descent on large language models by a larger margin than on other tasks, but it is unclear why. We show that a key factor in this performance gap is the heavy-tailed class imbalance found in…

Machine Learning · Computer Science 2024-07-15 Frederik Kunstner , Robin Yadav , Alan Milligan , Mark Schmidt , Alberto Bietti

Selecting an optimizer is a central step in the contemporary deep learning pipeline. In this paper, we demonstrate the sensitivity of optimizer comparisons to the hyperparameter tuning protocol. Our findings suggest that the hyperparameter…

Machine Learning · Computer Science 2020-06-17 Dami Choi , Christopher J. Shallue , Zachary Nado , Jaehoon Lee , Chris J. Maddison , George E. Dahl

Adam and AdamW are a class of default optimizers for training deep learning models in machine learning. These adaptive algorithms converge faster but generalize worse compared to SGD. In fact, their proved generalization error…

Machine Learning · Computer Science 2026-03-04 Feihu Huang , Guanyi Zhang , Songcan Chen

We prove that the Beta random walk has second order cubic fluctuations from the large deviation principle of the GUE Tracy-Widom type for arbitrary values $\upalpha>0$ and $\upbeta>0$ of the parameters of the Beta distribution, removing…

Probability · Mathematics 2022-04-15 Giancarlos Oviedo , Gonzalo Panizo , Alejandro F. Ramírez

In unconstrained optimisation on an Euclidean space, to prove convergence in Gradient Descent processes (GD) $x_{n+1}=x_n-\delta _n \nabla f(x_n)$ it usually is required that the learning rates $\delta _n$'s are bounded: $\delta _n\leq…

Optimization and Control · Mathematics 2020-01-09 Tuyen Trung Truong

Gradient Descent Ascent (GDA) methods are the mainstream algorithms for minimax optimization in generative adversarial networks (GANs). Convergence properties of GDA have drawn significant interest in the recent literature. Specifically,…

Optimization and Control · Mathematics 2022-07-05 Haochuan Li , Farzan Farnia , Subhro Das , Ali Jadbabaie

Many machine learning and optimization algorithms are built upon the framework of stochastic approximation (SA), for which the selection of step-size (or learning rate) $\{\alpha_n\}$ is crucial for success. An essential condition for…

Statistics Theory · Mathematics 2025-08-05 Caio Kalil Lauand , Sean Meyn

Linear TD($\lambda$) is one of the most fundamental reinforcement learning algorithms for policy evaluation. Previously, convergence rates are typically established under the assumption of linearly independent features, which does not hold…

Machine Learning · Computer Science 2025-10-15 Zixuan Xie , Xinyu Liu , Rohan Chandra , Shangtong Zhang

Efficient computation of min-max problems is a central question in optimization, learning, games, and controls. Arguably the most natural algorithm is gradient-descent-ascent (GDA). However, since the 1970s, conventional wisdom has argued…

Optimization and Control · Mathematics 2025-05-05 Henry Shugart , Jason M. Altschuler

This thesis contributes to the theoretical understanding of local update algorithms, especially Local SGD, in distributed and federated optimization under realistic models of data heterogeneity. A central focus is on the bounded…

Machine Learning · Computer Science 2025-07-02 Kumar Kshitij Patel

Generative data augmentation, which scales datasets by obtaining fake labeled examples from a trained conditional generative model, boosts classification performance in various learning tasks including (semi-)supervised learning, few-shot…

Machine Learning · Computer Science 2023-05-30 Chenyu Zheng , Guoqiang Wu , Chongxuan Li