English
Related papers

Related papers: An Amendment of Fast Subspace Tracking Methods

200 papers

Stochastic Gradient Descent (SGD) is a popular tool in training large-scale machine learning models. Its performance, however, is highly variable, depending crucially on the choice of the step sizes. Accordingly, a variety of strategies for…

Machine Learning · Statistics 2021-06-11 Xiaoyu Li , Zhenxun Zhuang , Francesco Orabona

We present a high-dimensional analysis of three popular algorithms, namely, Oja's method, GROUSE and PETRELS, for subspace estimation from streaming and highly incomplete observations. We show that, with proper time scaling, the…

Machine Learning · Computer Science 2019-01-30 Chuang Wang , Yonina C. Eldar , Yue M. Lu

The problem of increasing the accuracy of an approximate solution is considered for boundary value problems for parabolic equations. For ordinary differential equations (ODEs), nonstandard finite difference schemes are in common use for…

Numerical Analysis · Computer Science 2017-05-22 Petr N. Vabishchevich

Minimizing a convex function of a measure with a sparsity-inducing penalty is a typical problem arising, e.g., in sparse spikes deconvolution or two-layer neural networks training. We show that this problem can be solved by discretizing the…

Optimization and Control · Mathematics 2020-11-04 Lenaic Chizat

This paper analyzes a (1, $\lambda$)-Evolution Strategy, a randomized comparison-based adaptive search algorithm, optimizing a linear function with a linear constraint. The algorithm uses resampling to handle the constraint. Two cases are…

Optimization and Control · Mathematics 2015-10-16 Alexandre Chotard , Anne Auger , Nikolaus Hansen

A new measure to characterize stability of complex dynamical systems against large perturbation is suggested, the stability threshold (ST). It quantifies the magnitude of the weakest perturbation capable to disrupt the system and switch it…

Chaotic Dynamics · Physics 2016-01-06 Vladimir V. Klinshov , Vladimir I. Nekorkin , Jürgen Kurths

Space-time adaptive processing (STAP) algorithms with coprime arrays can provide good clutter suppression potential with low cost in airborne radar systems as compared with their uniform linear arrays counterparts. However, the performance…

Signal Processing · Electrical Eng. & Systems 2020-01-07 X. Wang , Z. Yang , J. Huang , R. C. de Lamare

Q-learning and SARSA are foundational reinforcement learning algorithms whose practical success depends critically on step-size calibration. Step-sizes that are too large can cause numerical instability, while step-sizes that are too small…

Machine Learning · Statistics 2026-01-28 Hwanwoo Kim , Eric Laber

Recent results show that vanilla gradient descent can be accelerated for smooth convex objectives, merely by changing the stepsize sequence. We show that this can lead to surprisingly large errors indefinitely, and therefore ask: Is there…

Optimization and Control · Mathematics 2024-06-21 Guy Kornowski , Ohad Shamir

Adam is a popular variant of stochastic gradient descent for finding a local minimizer of a function. In the constant stepsize regime, assuming that the objective function is differentiable and non-convex, we establish the convergence in…

Machine Learning · Statistics 2020-05-15 Anas Barakat , Pascal Bianchi

We consider randomized block coordinate stochastic mirror descent (RBSMD) methods for solving high-dimensional stochastic optimization problems with strongly convex objective functions. Our goal is to develop RBSMD schemes that achieve a…

Optimization and Control · Mathematics 2019-02-15 Nahidsadat Majlesinasab , Farzad Yousefian , Arash Pourhabib

At fine lattice spacings, lattice simulations are plagued by slow (topological) modes that give rise to large autocorrelation times. These, in turn, lead to statistical and systematic errors that are difficult to estimate. We study the…

High Energy Physics - Lattice · Physics 2025-03-14 Timo Eichhorn , Christian Hoelbling , Philip Rouenhoff , Lukas Varnhorst

Gradient Descent (GD) is a powerful workhorse of modern machine learning thanks to its scalability and efficiency in high-dimensional spaces. Its ability to find local minimisers is only guaranteed for losses with Lipschitz gradients, where…

Machine Learning · Computer Science 2023-07-27 Lei Chen , Joan Bruna

The computation time required by standard finite difference methods with fixed timesteps for solving fractional diffusion equations is usually very large because the number of operations required to find the solution scales as the square of…

Numerical Analysis · Mathematics 2024-06-28 Santos B. Yuste , Joaquin Quintana-Murillo

Stochastic gradient descent updates parameters with summation gradient computed from a random data batch. This summation will lead to unbalanced training process if the data we obtained is unbalanced. To address this issue, this paper takes…

Machine Learning · Computer Science 2019-05-22 Tao Yi , Xingxuan Wang

Empirical modelling often aims for the simplest model consistent with the data. A new technique is presented which quantifies the consistency of the model dynamics as a function of location in state space. As is well-known, traditional…

Chaotic Dynamics · Physics 2009-11-10 Patrick E. McSharry , Leonard A. Smith

The useful dynamic range of an image in the diffraction limited regime is usually limited by speckles caused by residual phase errors in the optical system forming the image. The technique of speckle decorrelation involves introducing many…

Astrophysics · Physics 2007-05-23 Anand Sivaramakrishnan , James P. Lloyd , Philip E. Hodge , Bruce A. Macintosh

SARAH and SPIDER are two recently developed stochastic variance-reduced algorithms, and SPIDER has been shown to achieve a near-optimal first-order oracle complexity in smooth nonconvex optimization. However, SPIDER uses an…

Optimization and Control · Mathematics 2020-05-19 Zhe Wang , Kaiyi Ji , Yi Zhou , Yingbin Liang , Vahid Tarokh

We propose a single-loop variance-reduced acceleration framework, which relates checkpoint update probabilities to momentum parameters, for solving the composite general convex problem where the smooth part has the finite-sum structure.…

Optimization and Control · Mathematics 2026-02-26 Hai Liu , Tiande Guo , Congying Han

Given a set P of n points in |R^d, an eps-kernel K subset P approximates the directional width of P in every direction within a relative (1-eps) factor. In this paper we study the stability of eps-kernels under dynamic insertion and…

Computational Geometry · Computer Science 2010-03-31 Pankaj K. Agarwal , Jeff M. Phillips , Hai Yu