English
Related papers

Related papers: KrADagrad: Kronecker Approximation-Domination Grad…

200 papers

There is growing evidence of the effectiveness of Shampoo, a higher-order preconditioning method, over Adam in deep learning optimization tasks. However, Shampoo's drawbacks include additional hyperparameters and computational overhead when…

Machine Learning · Computer Science 2025-02-03 Nikhil Vyas , Depen Morwani , Rosie Zhao , Mujin Kwun , Itai Shapira , David Brandfonbrener , Lucas Janson , Sham Kakade

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

High-dimensional Kronecker-structured estimation faces a conflict between non-convex scaling ambiguities and statistical robustness. The arbitrary factor scaling distorts gradient magnitudes, rendering standard fixed-threshold robust…

Methodology · Statistics 2025-12-23 Xiaoyu Zhang , Zhiyun Fan , Wenyang Zhang , Di Wang

Kronecker-factored Approximate Curvature (K-FAC) has recently been shown to converge faster in deep neural network (DNN) training than stochastic gradient descent (SGD); however, K-FAC's larger memory footprint hinders its applicability to…

Machine Learning · Computer Science 2021-09-21 J. Gregory Pauloski , Qi Huang , Lei Huang , Shivaram Venkataraman , Kyle Chard , Ian Foster , Zhao Zhang

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

The adaptive gradient online learning method known as AdaGrad has seen widespread use in the machine learning community in stochastic and adversarial online learning problems and more recently in deep learning methods. The method's…

Machine Learning · Computer Science 2016-10-05 Nishant A. Mehta , Alistair Rendell , Anish Varghese , Christfried Webers

In this paper we investigate the use of half-precision Kronecker product singular value decomposition (SVD) approximations as preconditioners for large-scale Tikhonov regularized least squares problems. Half precision reduces storage…

Numerical Analysis · Mathematics 2023-11-28 Yizhou Chen , Xiang Ji , James Nagy

Large pre-trained Transformer models achieve state-of-the-art results across diverse language and reasoning tasks, but full fine-tuning incurs substantial storage, memory, and computational overhead. Parameter-efficient fine-tuning (PEFT)…

Machine Learning · Computer Science 2025-06-19 Yee Hin Chong , Peng Qu

Many training methods, such as Adam(W) and Shampoo, learn a positive-definite curvature matrix and apply an inverse root before preconditioning. Recently, non-diagonal training methods, such as Shampoo, have gained significant attention;…

Machine Learning · Statistics 2025-03-31 Wu Lin , Felix Dangel , Runa Eschenhagen , Juhan Bae , Richard E. Turner , Roger B. Grosse

We propose a new stochastic first-order algorithmic framework to solve stochastic composite nonconvex optimization problems that covers both finite-sum and expectation settings. Our algorithms rely on the SARAH estimator introduced in…

Optimization and Control · Mathematics 2019-04-01 Nhan H. Pham , Lam M. Nguyen , Dzung T. Phan , Quoc Tran-Dinh

Given its widespread application in machine learning and optimization, the Kronecker product emerges as a pivotal linear algebra operator. However, its computational demands render it an expensive operation, leading to heightened costs in…

Data Structures and Algorithms · Computer Science 2024-02-14 Yeqi Gao , Zhao Song , Ruizhe Zhang

We consider the problem of matrix approximation and denoising induced by the Kronecker product decomposition. Specifically, we propose to approximate a given matrix by the sum of a few Kronecker products of matrices, which we refer to as…

Statistics Theory · Mathematics 2020-08-28 Chencheng Cai , Rong Chen , Han Xiao

Kronecker Products (KP) have been used to compress IoT RNN Applications by 15-38x compression factors, achieving better results than traditional compression methods. However when KP is applied to large Natural Language Processing tasks, it…

Machine Learning · Computer Science 2020-11-18 Urmish Thakker , Paul N. Whatmough , Zhi-Gang Liu , Matthew Mattina , Jesse Beu

We propose KFCPO, a novel Safe Reinforcement Learning (Safe RL) algorithm that combines scalable Kronecker-Factored Approximate Curvature (K-FAC) based second-order policy optimization with safety-aware gradient manipulation. KFCPO…

Machine Learning · Computer Science 2025-11-04 Joonyoung Lim , Younghwan Yoo

Reducing the test time resource requirements of a neural network while preserving test accuracy is crucial for running inference on resource-constrained devices. To achieve this goal, we introduce a novel network reparameterization based on…

Machine Learning · Computer Science 2019-05-16 Chaoqi Wang , Roger Grosse , Sanja Fidler , Guodong Zhang

Second-order methods hold significant promise for enhancing the convergence of deep neural network training; however, their large memory and computational demands have limited their practicality. Thus there is a need for scalable…

Machine Learning · Computer Science 2023-11-17 Fnu Devvrit , Sai Surya Duvvuri , Rohan Anil , Vineet Gupta , Cho-Jui Hsieh , Inderjit Dhillon

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

Modern adaptive optimization methods, such as Adam and its variants, have emerged as the most widely used tools in deep learning over recent years. These algorithms offer automatic mechanisms for dynamically adjusting the update step based…

Machine Learning · Computer Science 2025-02-12 Son Nguyen , Bo Liu , Lizhang Chen , Qiang Liu

Shampoo with Adam in the Preconditioner's eigenbasis (SOAP) has recently emerged as a promising optimization algorithm for neural network training, achieving superior training efficiency over both Adam and Shampoo in language modeling…

Machine Learning · Computer Science 2025-09-30 Yanqing Lu , Letao Wang , Jinbo Liu

Shampoo is one of the leading approximate second-order optimizers: a variant of it has won the MLCommons AlgoPerf competition, and it has been shown to produce models with lower activation outliers that are easier to compress. Yet, applying…

Machine Learning · Computer Science 2026-02-03 Ionut-Vlad Modoranu , Philip Zmushko , Erik Schultheis , Mher Safaryan , Dan Alistarh