English
Related papers

Related papers: Kronecker-factored Quasi-Newton Methods for Deep L…

200 papers

Recurrent neural networks (RNNs) are powerful in the tasks oriented to sequential data, such as natural language processing and video recognition. However, since the modern RNNs, including long-short term memory (LSTM) and gated recurrent…

Computer Vision and Pattern Recognition · Computer Science 2021-09-27 Dingheng Wang , Bijiao Wu , Guangshe Zhao , Man Yao , Hengnu Chen , Lei Deng , Tianyi Yan , Guoqi Li

Newton's method may exhibit slower convergence than vanilla Gradient Descent in its initial phase on strongly convex problems. Classical Newton-type multilevel methods mitigate this but, like Gradient Descent, achieve only linear…

Optimization and Control · Mathematics 2026-02-25 Nick Tsipinakis , Panos Parpas , Matthias Voigt

Newton's method may exhibit slower convergence than vanilla Gradient Descent in its initial phase on strongly convex problems. Classical Newton-type multilevel methods mitigate this but, like Gradient Descent, achieve only linear…

Optimization and Control · Mathematics 2026-03-05 Nick Tsipinakis , Panagiotis Tigkas , Panos Parpas

Laplace approximation (LA) and its linearized variant (LLA) enable effortless adaptation of pretrained deep neural networks to Bayesian neural networks. The generalized Gauss-Newton (GGN) approximation is typically introduced to improve…

Machine Learning · Computer Science 2022-10-25 Zhijie Deng , Feng Zhou , Jun Zhu

Optimization plays a key role in machine learning. Recently, stochastic second-order methods have attracted much attention due to their low computational cost in each iteration. However, these algorithms might perform poorly especially if…

Machine Learning · Computer Science 2017-10-25 Haishan Ye , Zhihua Zhang

Second-order information, in the form of Hessian- or Inverse-Hessian-vector products, is a fundamental tool for solving optimization problems. Recently, there has been significant interest in utilizing this information in the context of…

Machine Learning · Computer Science 2020-11-26 Sidak Pal Singh , Dan Alistarh

We propose Deep Kronecker Network (DKN), a novel framework designed for analyzing medical imaging data, such as MRI, fMRI, CT, etc. Medical imaging data is different from general images in at least two aspects: i) sample size is usually…

Machine Learning · Statistics 2025-12-25 Long Feng , Guang Yang

In this paper we present a review of the connections between classical algorithms for solving Markov Decision Processes (MDPs) and classical gradient-based algorithms in convex optimization. Some of these connections date as far back as the…

Optimization and Control · Mathematics 2021-11-29 Julien Grand-Clément

We propose a novel technique for faster deep neural network training which systematically applies sample-based approximation to the constituent tensor operations, i.e., matrix multiplications and convolutions. We introduce new sampling…

Machine Learning · Computer Science 2021-10-27 Menachem Adelman , Kfir Y. Levy , Ido Hakimi , Mark Silberstein

Deep learning methods have been shown to be effective in representing ground-state wave functions of quantum many-body systems. Existing methods use convolutional neural networks (CNNs) for square lattices due to their image-like…

Quantum Physics · Physics 2022-06-16 Cong Fu , Xuan Zhang , Huixin Zhang , Hongyi Ling , Shenglong Xu , Shuiwang Ji

The second-order optimization methods, notably the D-KFAC (Distributed Kronecker Factored Approximate Curvature) algorithms, have gained traction on accelerating deep neural network (DNN) training on GPU clusters. However, existing D-KFAC…

Machine Learning · Computer Science 2022-07-01 Lin Zhang , Shaohuai Shi , Wei Wang , Bo Li

Stochastic gradient descent (SGD) now acts as a fundamental part of optimization in current machine learning. Meanwhile, deep learning architectures have shown outstanding performance in a wide range of fields, such as natural language…

Machine Learning · Computer Science 2026-01-27 Zhao Song , Song Yue

Recently, the nearest Kronecker product (NKP) decomposition-based normalized least mean square (NLMS-NKP) algorithm has demonstrated superior convergence performance compared to the conventional NLMS algorithm. However, its convergence rate…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-16 Jianhong Ye , Haiquan Zhao

Optimization is important in machine learning problems, and quasi-Newton methods have a reputation as the most efficient numerical schemes for smooth unconstrained optimization. In this paper, we consider the explicit superlinear…

Optimization and Control · Mathematics 2022-09-13 Dachao Lin , Haishan Ye , Zhihua Zhang

Training learned image compression (LIC) models entails navigating a challenging optimization landscape defined by the fundamental trade-off between rate and distortion. Standard first-order optimizers, such as SGD and Adam, struggle with…

Image and Video Processing · Electrical Eng. & Systems 2026-01-30 Yichi Zhang , Fengqing Zhu

We present a novel algorithmic approach and an error analysis leveraging Quasi-Monte Carlo points for training deep neural network (DNN) surrogates of Data-to-Observable (DtO) maps in engineering design. Our analysis reveals higher-order…

Numerical Analysis · Mathematics 2020-09-08 M. Longo , S. Mishra , T. K. Rusch , Ch. Schwab

Federated learning (FL) is a promising technology that enables edge devices/clients to collaboratively and iteratively train a machine learning model under the coordination of a central server. The most common approach to FL is first-order…

Machine Learning · Computer Science 2025-01-22 Shayan Mohajer Hamidi , Linfeng Ye

This paper proposes a nonmonotone proximal quasi-Newton algorithm for unconstrained convex multiobjective composite optimization problems. To design the search direction, we minimize the max-scalarization of the variations of the Hessian…

Optimization and Control · Mathematics 2023-10-04 Xiaoxue Jiang

We show that, for finite-sum minimization problems, incorporating partial second-order information of the objective function can dramatically improve the robustness to mini-batch size of variance-reduced stochastic gradient methods, making…

Optimization and Control · Mathematics 2024-04-24 Sachin Garg , Albert S. Berahas , Michał Dereziński

This paper proposes a novel class of block quasi-Newton methods for convex optimization which we call symmetric rank-$k$ (SR-$k$) methods. Each iteration of SR-$k$ incorporates the curvature information with~$k$ Hessian-vector products…

Optimization and Control · Mathematics 2024-07-25 Chengchang Liu , Cheng Chen , Luo Luo
‹ Prev 1 3 4 5 6 7 10 Next ›