English
Related papers

Related papers: ODE approximation for the Adam algorithm: General …

200 papers

In this work, we propose a novel optimization model termed "sum-of-minimum" optimization. This model seeks to minimize the sum or average of $N$ objective functions over $k$ parameters, where each objective takes the minimum value of a…

Optimization and Control · Mathematics 2024-06-11 Lisang Ding , Ziang Chen , Xinshang Wang , Wotao Yin

Adam has been widely adopted for training deep neural networks due to less hyperparameter tuning and remarkable performance. To improve generalization, Adam is typically used in tandem with a squared $\ell_2$ regularizer (referred to as…

Machine Learning · Computer Science 2022-02-02 Zhenxun Zhuang , Mingrui Liu , Ashok Cutkosky , Francesco Orabona

Deep learning optimization relies heavily on the assumption of smooth loss landscapes, a condition systematically violated by modern architectures due to non-smooth components such as ReLU activations and quantization operators. In such…

Machine Learning · Computer Science 2026-05-29 Ruoran Xu , Borong She , Xiaobo Jin , Qiufeng Wang

We present a class of novel optimisers for training neural networks that makes use of the Riemannian metric naturally induced when the loss landscape is embedded in higher-dimensional space. This is the same metric that underlies common…

Machine Learning · Computer Science 2025-09-05 Thomas R. Harvey

We present a stochastic setting for optimization problems with nonsmooth convex separable objective functions over linear equality constraints. To solve such problems, we propose a stochastic Alternating Direction Method of Multipliers…

Machine Learning · Computer Science 2013-01-23 Hua Ouyang , Niao He , Alexander Gray

Normalization techniques are a boon for modern deep learning. They let weights converge more quickly with often better generalization performances. It has been argued that the normalization-induced scale invariance among the weights…

Machine Learning · Computer Science 2021-01-19 Byeongho Heo , Sanghyuk Chun , Seong Joon Oh , Dongyoon Han , Sangdoo Yun , Gyuwan Kim , Youngjung Uh , Jung-Woo Ha

Multi-objective gradient methods are becoming the standard for solving multi-objective problems. Among others, they show promising results in developing multi-objective recommender systems with both correlated and conflicting objectives.…

Machine Learning · Computer Science 2021-09-02 Blagoj Mitrevski , Milena Filipovic , Diego Antognini , Emma Lejal Glaude , Boi Faltings , Claudiu Musat

A recent line of research has shown that gradient-based algorithms with random initialization can converge to the global minima of the training loss for over-parameterized (i.e., sufficiently wide) deep neural networks. However, the…

Machine Learning · Computer Science 2019-06-12 Difan Zou , Quanquan Gu

The aim of this paper is to prove the exponential convergence, local and global, of Adam algorithm under precise conditions on the parameters, when the objective function lacks differentiability. More precisely, we require Lipschitz…

Optimization and Control · Mathematics 2024-03-14 Juan Ferrera , Javier Gómez Gil

We provide a new proof of the linear convergence of the alternating direction method of multipliers (ADMM) when one of the objective terms is strongly convex. Our proof is based on a framework for analyzing optimization algorithms…

Optimization and Control · Mathematics 2015-05-20 Robert Nishihara , Laurent Lessard , Benjamin Recht , Andrew Packard , Michael I. Jordan

In this paper, we investigate the convergence properties of a wide class of Adam-family methods for minimizing quadratically regularized nonsmooth nonconvex optimization problems, especially in the context of training nonsmooth neural…

Optimization and Control · Mathematics 2023-10-16 Kuangyu Ding , Nachuan Xiao , Kim-Chuan Toh

We propose a distributed algorithm based on Alternating Direction Method of Multipliers (ADMM) to minimize the sum of locally known convex functions using communication over a network. This optimization problem emerges in many applications…

Optimization and Control · Mathematics 2016-01-05 Ali Makhdoumi , Asuman Ozdaglar

Practical results have shown that deep learning optimizers using small constant learning rates, hyperparameters close to one, and large batch sizes can find the model parameters of deep neural networks that minimize the loss functions. We…

Machine Learning · Computer Science 2022-08-23 Hideaki Iiduka

Adaptive optimizers are the de facto standard in non-private training as they often enable faster convergence and improved performance. In contrast, differentially private (DP) training is still predominantly performed with DP-SGD,…

Machine Learning · Computer Science 2025-12-01 Mihaela Hudişteanu , Nikita P. Kalinin , Edwige Cyffers

First-order adaptive optimization methods like Adam are the default choices for training modern deep neural networks. Despite their empirical success, the theoretical understanding of these methods in non-smooth settings, particularly in…

Machine Learning · Statistics 2025-05-22 Anupama Sridhar , Alexander Johansen

Optimal Transport (OT) based distances are powerful tools for machine learning to compare probability measures and manipulate them using OT maps. In this field, a setting of interest is semi-discrete OT, where the source measure $\mu$ is…

Optimization algorithms are core methods by which machine learning models iteratively minimize loss functions, update parameters, learn from data, and improve performance. Momentum SGD and AdamW represent two important optimization…

Machine Learning · Computer Science 2026-05-21 Meng Zhu , Quan Xiao , Weidong Min

Adaptive gradient-based optimizers such as Adagrad and Adam are crucial for achieving state-of-the-art performance in machine translation and language modeling. However, these methods maintain second-order statistics for each parameter,…

Machine Learning · Computer Science 2019-09-13 Rohan Anil , Vineet Gupta , Tomer Koren , Yoram Singer

An algorithm capable of finding a likely global optimum (minimum) and a set of sub-optimal points for arbitrary generic functions of several variables is presented. The algorithm is designed to deal even with functions of complex behavior,…

Optimization and Control · Mathematics 2017-08-23 Glauco Masotti

In previous literature, backward error analysis was used to find ordinary differential equations (ODEs) approximating the gradient descent trajectory. It was found that finite step sizes implicitly regularize solutions because terms…

Machine Learning · Computer Science 2024-06-18 Matias D. Cattaneo , Jason M. Klusowski , Boris Shigida