English
Related papers

Related papers: MTAdam: Automatic Balancing of Multiple Training L…

200 papers

We introduce AdamS, a simple yet effective alternative to Adam for large language model (LLM) pretraining and post-training. By leveraging a novel denominator, i.e., the root of weighted sum of squares of the momentum and the current…

Machine Learning · Computer Science 2025-05-23 Huishuai Zhang , Bohan Wang , Luoxin Chen

We introduce a novel framework for the estimation of the posterior distribution over the weights of a neural network, based on a new probabilistic interpretation of adaptive optimisation algorithms such as AdaGrad and Adam. We demonstrate…

Machine Learning · Statistics 2020-07-21 Samuel Kessler , Arnold Salas , Vincent W. C. Tan , Stefan Zohren , Stephen Roberts

To mitigate the negative effect of low quality training data on the performance of neural machine translation models, most existing strategies focus on filtering out harmful data before training starts. In this paper, we explore strategies…

Computation and Language · Computer Science 2021-03-01 Xinyi Wang , Ankur Bapna , Melvin Johnson , Orhan Firat

Deep neural network learning can be formulated as a non-convex optimization problem. Existing optimization algorithms, e.g., Adam, can learn the models fast, but may get stuck in local optima easily. In this paper, we introduce a novel…

Machine Learning · Computer Science 2019-03-12 Jiawei Zhang , Fisher B. Gouza

In this work, to efficiently help escape the stationary and saddle points, we propose, analyze, and generalize a stochastic strategy performed as an operator for a first-order gradient descent algorithm in order to increase the target…

Machine Learning · Computer Science 2022-05-23 Wei Zhang , Yu Bao

This work presents BAdam, an optimization method that leverages the block coordinate descent (BCD) framework with Adam's update rule. BAdam offers a memory efficient approach to the full parameter finetuning of large language models. We…

Machine Learning · Computer Science 2024-11-18 Qijun Luo , Hengxu Yu , Xiao Li

The vast majority of successful deep neural networks are trained using variants of stochastic gradient descent (SGD) algorithms. Recent attempts to improve SGD can be broadly categorized into two approaches: (1) adaptive learning rate…

Machine Learning · Computer Science 2019-12-04 Michael R. Zhang , James Lucas , Geoffrey Hinton , Jimmy Ba

Momentum based optimizers are central to a wide range of machine learning applications. These typically rely on an Exponential Moving Average (EMA) of gradients, which decays exponentially the present contribution of older gradients. This…

Machine Learning · Computer Science 2024-10-01 Matteo Pagliardini , Pierre Ablin , David Grangier

In this paper, we investigate the popular deep learning optimization routine, Adam, from the perspective of statistical moments. While Adam is an adaptive lower-order moment based (of the stochastic gradient) method, we propose an extension…

Machine Learning · Computer Science 2019-10-16 Zhanhong Jiang , Aditya Balu , Sin Yong Tan , Young M Lee , Chinmay Hegde , Soumik Sarkar

In recent years, deep learning has achieved remarkable success in various fields such as image recognition, natural language processing, and speech recognition. The effectiveness of deep learning largely depends on the optimization methods…

Machine Learning · Computer Science 2023-04-25 David Shulman

In the training of neural networks, adaptive moment estimation (Adam) typically converges fast but exhibits suboptimal generalization performance. A widely accepted explanation for its defect in generalization is that it often tends to…

Machine Learning · Computer Science 2026-03-10 Tao Shi , Liangming Chen , Long Jin , Mengchu Zhou

First-order stochastic optimization methods are currently the most widely used class of methods for training deep neural networks. However, the choice of the optimizer has become an ad-hoc rule that can significantly affect the performance.…

Machine Learning · Computer Science 2020-10-21 Samy Jelassi , Aaron Defazio

Learning rate adaptation is a popular topic in machine learning. Gradient Descent trains neural nerwork with a fixed learning rate. Learning rate adaptation is proposed to accelerate the training process through adjusting the step size in…

Machine Learning · Computer Science 2022-10-20 Bozhou Chen , Hongzhi Wang , Chenmin Ba

We study optimization for losses that admit a variance-mean scale-mixture representation. Under this representation, each EM iteration is a weighted least squares update in which latent variables determine observation and parameter weights;…

Computation · Statistics 2026-02-17 Nick Polson , Vadim Sokolov

We introduce MADGRAD, a novel optimization method in the family of AdaGrad adaptive gradient methods. MADGRAD shows excellent performance on deep learning optimization problems from multiple fields, including classification and…

Machine Learning · Computer Science 2021-08-27 Aaron Defazio , Samy Jelassi

The ADAM optimizer is exceedingly popular in the deep learning community. Often it works very well, sometimes it doesn't. Why? We interpret ADAM as a combination of two aspects: for each weight, the update direction is determined by the…

Machine Learning · Computer Science 2020-12-15 Lukas Balles , Philipp Hennig

We present multi-point optimization: an optimization technique that allows to train several models simultaneously without the need to keep the parameters of each one individually. The proposed method is used for a thorough empirical…

Machine Learning · Computer Science 2025-11-18 Ivan Skorokhodov , Mikhail Burtsev

In federated learning (FL), model training performance is strongly impacted by data heterogeneity across clients. Client-drift compensation methods have recently emerged as a solution to this issue, introducing correction terms into local…

Machine Learning · Computer Science 2025-05-20 Evan Chen , Shiqiang Wang , Jianing Zhang , Dong-Jun Han , Chaoyue Liu , Christopher Brinton

Training deep neural networks is a challenging task. In order to speed up training and enhance the performance of deep neural networks, we rectify the vanilla conjugate gradient as conjugate-gradient-like and incorporate it into the generic…

Machine Learning · Computer Science 2025-01-09 Jiawu Tian , Liwei Xu , Xiaowei Zhang , Yongqi Li

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