English
Related papers

Related papers: MAC: An Efficient Gradient Preconditioning using M…

200 papers

A key challenge for gradient based optimization methods in model-free reinforcement learning is to develop an approach that is sample efficient and has low variance. In this work, we apply Kronecker-factored curvature estimation technique…

Machine Learning · Computer Science 2018-12-12 Mohammad Firouzi

Second order stochastic optimizers allow parameter update step size and direction to adapt to loss curvature, but have traditionally required too much memory and compute for deep learning. Recently, Shampoo [Gupta et al., 2018] introduced a…

Machine Learning · Statistics 2023-06-01 Jonathan Mei , Alexander Moreno , Luke Walters

K-FAC is a successful tractable implementation of Natural Gradient for Deep Learning, which nevertheless suffers from the requirement to compute the inverse of the Kronecker factors (through an eigen-decomposition). This can be very…

Machine Learning · Computer Science 2022-11-28 Constantin Octavian Puiu

In this technical report, we consider an approach that combines the PPO objective and K-FAC natural gradient optimization, for which we call PPOKFAC. We perform a range of empirical analysis on various aspects of the algorithm, such as…

Artificial Intelligence · Computer Science 2018-01-18 Jiaming Song , Yuhuai Wu

Distributed training with synchronous stochastic gradient descent (SGD) on GPU clusters has been widely used to accelerate the training process of deep models. However, SGD only utilizes the first-order gradient in model parameter updates,…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-07-15 Shaohuai Shi , Lin Zhang , Bo Li

The Variational Monte Carlo method has recently seen important advances through the use of neural network quantum states. While more and more sophisticated ans\"atze have been designed to tackle a wide variety of quantum many-body problems,…

Nuclear Theory · Physics 2025-07-09 M. Drissi , J. W. T. Keeble , J. Rozalén Sarmiento , A. Rios

We propose a quadratic penalty method for continual learning of neural networks that contain batch normalization (BN) layers. The Hessian of a loss function represents the curvature of the quadratic penalty function, and a…

Machine Learning · Computer Science 2020-04-17 Janghyeon Lee , Hyeong Gwon Hong , Donggyu Joo , Junmo Kim

This research delves into the role of the quantum Fisher Information Matrix (FIM) in enhancing the performance of Parameterized Quantum Circuit (PQC)-based reinforcement learning agents. While previous studies have highlighted the…

Quantum Physics · Physics 2024-01-17 André Sequeira , Luis Paulo Santos , Luis Soares Barbosa

This paper establishes a mathematical foundation for the Adam optimizer, elucidating its connection to natural gradient descent through Riemannian and information geometry. We provide an accessible and detailed analysis of the diagonal…

Machine Learning · Computer Science 2024-09-05 Dongseong Hwang

We study the training dynamics of gradient descent in a softmax self-attention layer trained to perform linear regression and show that a simple first-order optimization algorithm can converge to the globally optimal self-attention…

Machine Learning · Computer Science 2026-03-03 Gautam Goel , Mahdi Soltanolkotabi , Peter Bartlett

Deep neural networks (DNNs) are currently predominantly trained using first-order methods. Some of these methods (e.g., Adam, AdaGrad, and RMSprop, and their variants) incorporate a small amount of curvature information by using a diagonal…

Machine Learning · Computer Science 2022-10-28 Achraf Bahamou , Donald Goldfarb , Yi Ren

In stochastic optimization, using large batch sizes during training can leverage parallel resources to produce faster wall-clock training times per training epoch. However, for both training loss and testing error, recent results analyzing…

Machine Learning · Computer Science 2021-04-21 Linjian Ma , Gabe Montague , Jiayu Ye , Zhewei Yao , Amir Gholami , Kurt Keutzer , Michael W. Mahoney

Recently mean field theory has been successfully used to analyze properties of wide, random neural networks. It gave rise to a prescriptive theory for initializing feed-forward neural networks with orthogonal weights, which ensures that…

Machine Learning · Statistics 2019-06-05 Piotr A. Sokol , Il Memming Park

Standard gradient descent methods are susceptible to a range of issues that can impede training, such as high correlations and different scaling in parameter space.These difficulties can be addressed by second-order approaches that apply a…

Machine Learning · Computer Science 2020-04-29 Ted Moskovitz , Rui Wang , Janice Lan , Sanyam Kapoor , Thomas Miconi , Jason Yosinski , Aditya Rawal

Natural gradient descent has proven effective at mitigating the effects of pathological curvature in neural network optimization, but little is known theoretically about its convergence properties, especially for \emph{nonlinear} networks.…

Machine Learning · Statistics 2019-10-29 Guodong Zhang , James Martens , Roger Grosse

Second-order optimization methods, which leverage curvature information, offer faster and more stable convergence than first-order methods such as stochastic gradient descent (SGD) and Adam. However, their practical adoption is hindered by…

Emerging Technologies · Computer Science 2025-12-08 Saitao Zhang , Yubiao Luo , Shiqing Wang , Pushen Zuo , Yongxiang Li , Lunshuai Pan , Zheng Miao , Zhong Sun

The success of gradient descent in ML and especially for learning neural networks is remarkable and robust. In the context of how the brain learns, one aspect of gradient descent that appears biologically difficult to realize (if not…

Neural and Evolutionary Computing · Computer Science 2022-04-12 Shivam Garg , Santosh S. Vempala

In this work and its accompanying Part II [1], we develop an accelerated algorithmic framework, DAMA (Decentralized Accelerated Minimax Approach), for nonconvex Polyak-Lojasiewicz minimax optimization over decentralized multi-agent…

Optimization and Control · Mathematics 2025-12-17 Haoyuan Cai , Sulaiman A. Alghunaim , Ali H. Sayed

First-order optimization methods are currently the mainstream in training deep neural networks (DNNs). Optimizers like Adam incorporate limited curvature information by employing the diagonal matrix preconditioning of the stochastic…

Machine Learning · Computer Science 2025-03-12 Damien Martins Gomes , Yanlei Zhang , Eugene Belilovsky , Guy Wolf , Mahdi S. Hosseini

First-order optimization methods remain the standard for training deep neural networks (DNNs). Optimizers like Adam incorporate limited curvature information by preconditioning the stochastic gradient with a diagonal matrix. Despite the…

Machine Learning · Computer Science 2025-04-30 Damien Martins Gomes