English
Related papers

Related papers: Newton retraction as approximate geodesics on subm…

200 papers

The techniques and analysis presented in this paper provide new methods to solve optimization problems posed on Riemannian manifolds. A new point of view is offered for the solution of constrained optimization problems. Some classical…

Optimization and Control · Mathematics 2018-04-12 Steven Thomas Smith

Manifold learning is a central task in modern statistics and data science. Many datasets (cells, documents, images, molecules) can be represented as point clouds embedded in a high dimensional ambient space, however the degrees of freedom…

Machine Learning · Statistics 2025-02-18 Stephen Zhang , Gilles Mordant , Tetsuya Matsumoto , Geoffrey Schiebinger

Finding roots of equations is at the heart of most computational science. A well-known and widely used iterative algorithm is the Newton's method. However, its convergence depends heavily on the initial guess, with poor choices often…

Numerical Analysis · Mathematics 2020-04-09 Ankush Aggarwal , Sanjay Pant

We generalize Newton-type methods for minimizing smooth functions to handle a sum of two convex functions: a smooth function and a nonsmooth function with a simple proximal mapping. We show that the resulting proximal Newton-type methods…

Machine Learning · Statistics 2014-03-19 Jason D. Lee , Yuekai Sun , Michael A. Saunders

{A defining characteristic of Newton's method is local superlinear convergence within a neighbourhood of a strict local minimum. However, outside this neighborhood Newton's method can converge slowly or even diverge. A common approach to…

Optimization and Control · Mathematics 2025-09-19 Betty Shea , Mark Schmidt

Many machine learning problems involve regressing variables on a non-Euclidean manifold -- e.g. a discrete probability distribution, or the 6D pose of an object. One way to tackle these problems through gradient-based learning is to use a…

Computer Vision and Pattern Recognition · Computer Science 2021-10-14 Romain Brégier

Large scale optimization problems are ubiquitous in machine learning and data analysis and there is a plethora of algorithms for solving such problems. Many of these algorithms employ sub-sampling, as a way to either speed up the…

Optimization and Control · Mathematics 2016-02-29 Farbod Roosta-Khorasani , Michael W. Mahoney

We extend the class of SQP methods for equality constrained optimization to the setting of differentiable manifolds. The use of retractions and stratifications allows us to pull back the involved mappings to linear spaces. We study local…

Optimization and Control · Mathematics 2020-05-15 Anton Schiela , Julian Ortiz

We propose tensorial neural networks (TNNs), a generalization of existing neural networks by extending tensor operations on low order operands to those on high order ones. The problem of parameter learning is challenging, as it corresponds…

Machine Learning · Statistics 2018-12-11 Jiahao Su , Jingling Li , Bobby Bhattacharjee , Furong Huang

Newton-step approximations to pseudo maximum likelihood estimates of spatial autoregressive models with a large number of parameters are examined, in the sense that the parameter space grows slowly as a function of sample size. These have…

Econometrics · Economics 2021-05-25 Abhimanyu Gupta

As a popular channel pruning method for convolutional neural networks (CNNs), network slimming (NS) has a three-stage process: (1) it trains a CNN with $\ell_1$ regularization applied to the scaling factors of the batch normalization…

Computer Vision and Pattern Recognition · Computer Science 2024-01-31 Kevin Bui , Fanghui Xue , Fredrick Park , Yingyong Qi , Jack Xin

Neutron reflectometry (NR) is a powerful technique to probe surfaces and interfaces. NR is inherently an indirect measurement technique, access to the physical quantities of interest (layer thickness, scattering length density, roughness),…

We investigate the use of regularized Newton methods with adaptive norms for optimizing neural networks. This approach can be seen as a second-order counterpart of adaptive gradient methods, which we here show to be interpretable as…

Machine Learning · Computer Science 2020-09-29 Jonas Kohler , Leonard Adolphs , Aurelien Lucchi

In this paper, we investigate decentralized non-convex optimization with orthogonal constraints. Conventional algorithms for this setting require either manifold retractions or other types of projection to ensure feasibility, both of which…

Machine Learning · Computer Science 2024-12-10 Youbang Sun , Shixiang Chen , Alfredo Garcia , Shahin Shahrampour

A game theory inspired methodology is proposed for finding a function's saddle points. While explicit descent methods are known to have severe convergence issues, implicit methods are natural in an adversarial setting, as they take the…

Optimization and Control · Mathematics 2019-06-04 Montacer Essid , Esteban Tabak , Giulio Trigila

This paper focuses on minimizing a smooth function combined with a nonsmooth regularization term on a compact Riemannian submanifold embedded in the Euclidean space under a decentralized setting. Typically, there are two types of approaches…

Optimization and Control · Mathematics 2025-07-16 Lei Wang , Le Bao , Xin Liu

We analyse the convergence of the gradient projection algorithm, which is finalized with the Newton method, to a stationary point for the problem of nonconvex constrained optimization $\min_{x \in S} f(x)$ with a proximally smooth set $S =…

Optimization and Control · Mathematics 2019-12-11 Maxim Balashov , Andrey Tremba

Recently, the proximal Newton-type method and its variants have been generalized to solve composite optimization problems over the Stiefel manifold whose objective function is the summation of a smooth function and a nonsmooth function. In…

Optimization and Control · Mathematics 2025-02-11 Qinsi Wang , Wei Hong Yang

In this work, we propose an optimization algorithm which we call norm-adapted gradient descent. This algorithm is similar to other gradient-based optimization algorithms like Adam or Adagrad in that it adapts the learning rate of stochastic…

Machine Learning · Computer Science 2020-10-14 David Sprunger

We propose a Riemannian version of Nesterov's Accelerated Gradient algorithm (RAGD), and show that for geodesically smooth and strongly convex problems, within a neighborhood of the minimizer whose radius depends on the condition number as…

Optimization and Control · Mathematics 2018-06-08 Hongyi Zhang , Suvrit Sra