English
Related papers

Related papers: Optimizing Neural Networks with Kronecker-factored…

200 papers

The $k$-principal component analysis ($k$-PCA) problem is a fundamental algorithmic primitive that is widely-used in data analysis and dimensionality reduction applications. In statistical settings, the goal of $k$-PCA is to identify a top…

Numerical Analysis · Mathematics 2024-06-12 Arun Jambulapati , Syamantak Kumar , Jerry Li , Shourya Pandey , Ankit Pensia , Kevin Tian

In this paper, we propose a simple, fast and easy to implement algorithm LOSSGRAD (locally optimal step-size in gradient descent), which automatically modifies the step-size in gradient descent during neural networks training. Given a…

Machine Learning · Computer Science 2019-11-26 Bartosz Wójcik , Łukasz Maziarka , Jacek Tabor

Training deep neural networks (DNNs) efficiently is a challenge due to the associated highly nonconvex optimization. The backpropagation (backprop) algorithm has long been the most widely used algorithm for gradient computation of…

Machine Learning · Statistics 2018-03-28 Tim Tsz-Kit Lau , Jinshan Zeng , Baoyuan Wu , Yuan Yao

Rapid advances in data collection and processing capabilities have allowed for the use of increasingly complex models that give rise to nonconvex optimization problems. These formulations, however, can be arbitrarily difficult to solve in…

Multiagent Systems · Computer Science 2020-04-01 Stefan Vlaski , Ali H. Sayed

Stochastic gradient descent with backpropagation is the workhorse of artificial neural networks. It has long been recognized that backpropagation fails to be a biologically plausible algorithm. Fundamentally, it is a non-local procedure --…

Machine Learning · Statistics 2021-12-24 Ganlin Song , Ruitu Xu , John Lafferty

The k Nearest Neighbors (kNN) method has received much attention in the past decades, where some theoretical bounds on its performance were identified and where practical optimizations were proposed for making it work fairly well in high…

Machine Learning · Computer Science 2016-06-14 Aleksander Lodwich , Faisal Shafait , Thomas Breuel

Function fitting/approximation plays a fundamental role in computer graphics and other engineering applications. While recent advances have explored neural networks to address this task, these methods often rely on architectures with many…

Graphics · Computer Science 2025-05-28 Biao Zhang , Peter Wonka

We introduce Natural Neural Networks, a novel family of algorithms that speed up convergence by adapting their internal representation during training to improve conditioning of the Fisher matrix. In particular, we show a specific example…

Machine Learning · Statistics 2015-07-02 Guillaume Desjardins , Karen Simonyan , Razvan Pascanu , Koray Kavukcuoglu

One of the most important parts of Artificial Neural Networks is minimizing the loss functions which tells us how good or bad our model is. To minimize these losses we need to tune the weights and biases. Also to calculate the minimum value…

Machine Learning · Computer Science 2021-01-08 Kaustubh Yadav

First-order methods for stochastic optimization have undeniable relevance, in part due to their pivotal role in machine learning. Variance reduction for these algorithms has become an important research topic. In contrast to common…

Machine Learning · Computer Science 2021-09-08 Manuel Madeira , Renato Negrinho , João Xavier , Pedro M. Q. Aguiar

Graph drawing is a fundamental task in information visualization, with the Fruchterman--Reingold (FR) force model being one of the most popular choices. We can interpret this visualization task as a continuous optimization problem, which…

Computational Geometry · Computer Science 2025-03-04 Hiroki Hamaguchi , Naoki Marumo , Akiko Takeda

Deep neural networks (DNN) are typically optimized using stochastic gradient descent (SGD). However, the estimation of the gradient using stochastic samples tends to be noisy and unreliable, resulting in large gradient variance and bad…

Machine Learning · Computer Science 2021-05-18 Xingyi Yang

Substantial progress has been made recently on developing provably accurate and efficient algorithms for low-rank matrix factorization via nonconvex optimization. While conventional wisdom often takes a dim view of nonconvex optimization…

Machine Learning · Computer Science 2019-10-23 Yuejie Chi , Yue M. Lu , Yuxin Chen

Random Fourier features (RFF) represent one of the most popular and wide-spread techniques in machine learning to scale up kernel algorithms. Despite the numerous successful applications of RFFs, unfortunately, quite little is understood…

Machine Learning · Statistics 2019-02-12 Zoltan Szabo , Bharath K. Sriperumbudur

Natural Gradient Descent (NGD) is a second-order neural network training that preconditions the gradient descent with the inverse of the Fisher Information Matrix (FIM). Although NGD provides an efficient preconditioner, it is not…

Machine Learning · Computer Science 2022-10-12 Tran Van Sang , Mhd Irvan , Rie Shigetomi Yamaguchi , Toshiyuki Nakata

We propose a non-convex optimization algorithm, based on the Burer-Monteiro (BM) factorization, for the quantum process tomography problem, in order to estimate a low-rank process matrix $\chi$ for near-unitary quantum gates. In this work,…

Quantum Physics · Physics 2024-07-01 David A. Quiroga , Anastasios Kyrillidis

Second-order optimization algorithms exhibit excellent convergence properties for training deep learning models, but often incur significant computation and memory overheads. This can result in lower training efficiency than the first-order…

Machine Learning · Computer Science 2023-08-07 Lin Zhang , Shaohuai Shi , Bo Li

We develop a Frank-Wolfe algorithm with corrective steps, generalizing previous algorithms including blended conditional gradients, blended pairwise conditional gradients, and fully-corrective Frank-Wolfe. For this, we prove tight…

Optimization and Control · Mathematics 2026-05-21 Jannis Halbey , Seta Rakotomandimby , Mathieu Besançon , Sébastien Designolle , Sebastian Pokutta

Standard first-order stochastic optimization algorithms base their updates solely on the average mini-batch gradient, and it has been shown that tracking additional quantities such as the curvature can help de-sensitize common…

Machine Learning · Computer Science 2020-11-11 Ricky T. Q. Chen , Dami Choi , Lukas Balles , David Duvenaud , Philipp Hennig

Reinforcement learning is a growing field in AI with a lot of potential. Intelligent behavior is learned automatically through trial and error in interaction with the environment. However, this learning process is often costly. Using…

Quantum Physics · Physics 2023-12-08 Nico Meyer , Daniel D. Scherer , Axel Plinge , Christopher Mutschler , Michael J. Hartmann