English
Related papers

Related papers: Implicit Bias of AdamW: $\ell_\infty$ Norm Constra…

200 papers

Weight decay (WD) is a traditional regularization technique in deep learning, but despite its ubiquity, its behavior is still an area of active research. Golatkar et al. have recently shown that WD only matters at the start of the training…

Machine Learning · Computer Science 2020-12-29 Johan Bjorck , Kilian Weinberger , Carla Gomes

Over-parameterized deep networks trained using gradient-based optimizers are a popular choice for solving classification and ranking problems. Without appropriately tuned $\ell_2$ regularization or weight decay, such networks have the…

Machine Learning · Computer Science 2021-08-13 Aman Gupta , Rohan Ramanath , Jun Shi , Anika Ramachandran , Sirou Zhou , Mingzhou Zhou , S. Sathiya Keerthi

Adam is a widely used optimization algorithm in deep learning, yet the specific class of objective functions where it exhibits inherent advantages remains underexplored. Unlike prior studies requiring external schedulers and $\beta_2$ near…

Machine Learning · Computer Science 2026-05-26 Zhiwei Bai , Jiajie Zhao , Zhangchen Zhou , Zhi-Qin John Xu , Yaoyu Zhang

Adaptive first-order optimizers are fundamental tools in deep learning, although they may suffer from poor generalization due to the nonuniform gradient scaling. In this work, we propose AdamL, a novel variant of the Adam optimizer, that…

Machine Learning · Statistics 2023-12-27 Lu Xia , Stefano Massei

We formulate the problem of neural network optimization as Bayesian filtering, where the observations are the backpropagated gradients. While neural network optimization has previously been studied using natural gradient methods which are…

Machine Learning · Statistics 2020-04-17 Laurence Aitchison

Adam is a popular variant of stochastic gradient descent for finding a local minimizer of a function. In the constant stepsize regime, assuming that the objective function is differentiable and non-convex, we establish the convergence in…

Machine Learning · Statistics 2020-05-15 Anas Barakat , Pascal Bianchi

The generalization performance of deep neural networks with regard to the optimization algorithm is one of the major concerns in machine learning. This performance can be affected by various factors. In this paper, we theoretically prove…

Machine Learning · Computer Science 2023-08-23 Mohammad Lashkari , Amin Gheibi

The Adam optimizer is a cornerstone of modern deep learning, yet the empirical necessity of each of its individual components is often taken for granted. This paper presents a focused investigation into the role of bias-correction, a…

Machine Learning · Computer Science 2025-11-27 Sam Laing , Antonio Orvieto

Reinforcement learning (RL), particularly RL from verifiable reward (RLVR), has become a crucial phase of training large language models (LLMs) and a key focus of current scaling efforts. However, optimization practices in RL largely follow…

Machine Learning · Computer Science 2026-02-25 Sagnik Mukherjee , Lifan Yuan , Pavan Jayasinha , Dilek Hakkani-Tür , Hao Peng

Large language models (LLMs) have demonstrated impressive generalization and emergent capabilities, yet their pre-training remains computationally expensive and sensitive to optimization dynamics. While Adam-based optimizers offer fast…

Machine Learning · Computer Science 2025-10-01 Junjie Wang , Pan Zhou , Yiming Dong , Huan Li , Jia Li , Xun Zhou , Qicheng Lao , Cong Fang , Zhouchen Lin

We present Amos, a stochastic gradient-based optimizer designed for training deep neural networks. It can be viewed as an Adam optimizer with theoretically supported, adaptive learning-rate decay and weight decay. A key insight behind Amos…

Machine Learning · Computer Science 2022-11-22 Ran Tian , Ankur P. Parikh

Neural Collapse (NC) refers to the emergence of highly symmetric geometric structures in the representations of deep neural networks during the terminal phase of training. Despite its prevalence, the theoretical understanding of NC remains…

Machine Learning · Computer Science 2026-02-26 Jim Zhao , Tin Sum Cheng , Wojciech Masarczyk , Aurelien Lucchi

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

Many adaptive optimization methods have been proposed and used in deep learning, in which Adam is regarded as the default algorithm and widely used in many deep learning frameworks. Recently, many variants of Adam, such as Adabound, RAdam…

Machine Learning · Computer Science 2020-11-05 Wei Yuan , Kai-Xin Gao

In this paper, we made an extension to the convergence analysis of the dynamics of two-layered bias-free networks with one $ReLU$ output. We took into consideration two popular regularization terms: the $\ell_1$ and $\ell_2$ norm of the…

Machine Learning · Statistics 2017-11-21 Zhifeng Kong

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

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

While popular optimization methods such as SGD, AdamW, and Lion depend on steepest descent updates in either $\ell_2$ or $\ell_\infty$ norms, there remains a critical gap in handling the non-Euclidean structure observed in modern deep…

Machine Learning · Computer Science 2025-06-11 Xinyu Luo , Cedar Site Bai , Bolian Li , Petros Drineas , Ruqi Zhang , Brian Bullins

Deep learning methods - usually consisting of a class of deep neural networks (DNNs) trained by a stochastic gradient descent (SGD) optimization method - are nowadays omnipresent in data-driven learning problems as well as in scientific…

Optimization and Control · Mathematics 2025-01-13 Steffen Dereich , Arnulf Jentzen , Adrian Riekert

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