English
Related papers

Related papers: Negative curvature obstructs acceleration for stro…

200 papers

Optimization under structural constraints is typically analyzed through projection or penalty methods, obscuring the geometric mechanism by which constraints shape admissible dynamics. We propose an operator-theoretic formulation in which…

Optimization and Control · Mathematics 2026-03-10 Changkai Li

In this paper, we present an adaptive gradient descent method for geodesically convex optimization on a Riemannian manifold with nonnegative sectional curvature. The method automatically adapts to the local geometry of the function and does…

Optimization and Control · Mathematics 2025-09-16 Aban Ansari-Önnestam , Yura Malitsky

Linear optimization is many times algorithmically simpler than non-linear convex optimization. Linear optimization over matroid polytopes, matching polytopes and path polytopes are example of problems for which we have simple and efficient…

Machine Learning · Computer Science 2015-08-17 Dan Garber , Elad Hazan

Many classical and modern machine learning algorithms require solving optimization tasks under orthogonality constraints. Solving these tasks with feasible methods requires a gradient descent update followed by a retraction operation on the…

Optimization and Control · Mathematics 2024-12-10 Youbang Sun , Shixiang Chen , Alfredo Garcia , Shahin Shahrampour

Stochastic first-order methods are standard for training large-scale machine learning models. Random behavior may cause a particular run of an algorithm to result in a highly suboptimal objective value, whereas theoretical guarantees are…

Optimization and Control · Mathematics 2024-09-02 Eduard Gorbunov , Marina Danilova , Innokentiy Shibaev , Pavel Dvurechensky , Alexander Gasnikov

Quasar convexity is a condition that allows some first-order methods to efficiently minimize a function even when the optimization landscape is non-convex. Previous works develop near-optimal accelerated algorithms for minimizing this class…

Optimization and Control · Mathematics 2023-02-16 Jun-Kun Wang , Andre Wibisono

In Riemannian optimization, it is well known that the condition number of the Riemannian Hessian at an optimum strongly influences the asymptotic convergence behavior of optimization algorithms. On the manifold of symmetric positive…

Optimization and Control · Mathematics 2026-05-04 Derun Zhou , Keisuke Yano , Mahito Sugiyama

This work studies minimization problems with zero-order noisy oracle information under the assumption that the objective function is highly smooth and possibly satisfies additional properties. We consider two kinds of zero-order projected…

Statistics Theory · Mathematics 2023-06-06 Arya Akhavan , Evgenii Chzhen , Massimiliano Pontil , Alexandre B. Tsybakov

Recently, the high-resolution ordinary differential equation (ODE) framework, which retains higher-order terms, has been proposed to analyze gradient-based optimization algorithms. Through this framework, the term $\nabla^2…

Optimization and Control · Mathematics 2026-02-05 Xudong Li , Lei Shi , Mingqi Song

Many modern machine learning applications - from online principal component analysis to covariance matrix identification and dictionary learning - can be formulated as minimization problems on Riemannian manifolds, and are typically solved…

Optimization and Control · Mathematics 2023-11-07 Ya-Ping Hsieh , Mohammad Reza Karimi , Andreas Krause , Panayotis Mertikopoulos

We consider the problem of analyzing and designing gradient-based discrete-time optimization algorithms for a class of unconstrained optimization problems having strongly convex objective functions with Lipschitz continuous gradient. By…

Optimization and Control · Mathematics 2025-10-20 Simon Michalowsky , Carsten Scherer , Christian Ebenbauer

We propose a Riemannian gradient descent with the Poincar\'e metric to compute the order-$\alpha$ Augustin information, a widely used quantity for characterizing exponential error behaviors in information theory. We prove that the algorithm…

Information Theory · Computer Science 2024-05-10 Guan-Ren Wang , Chung-En Tsai , Hao-Chung Cheng , Yen-Huan Li

We study optimization over Riemannian embedded submanifolds, where the objective function is relatively smooth in the ambient Euclidean space. Such problems have broad applications but are still largely unexplored. We introduce two…

Optimization and Control · Mathematics 2025-08-08 Chang He , Jiaxiang Li , Bo Jiang , Shiqian Ma , Shuzhong Zhang

We introduce a novel geometry-informed irreversible perturbation that accelerates convergence of the Langevin algorithm for Bayesian computation. It is well documented that there exist perturbations to the Langevin dynamics that preserve…

Methodology · Statistics 2022-09-02 Benjamin J. Zhang , Youssef M. Marzouk , Konstantinos Spiliopoulos

It is known that when minimizing smooth Polyak-{\L}ojasiewicz (PL) functions, momentum algorithms cannot significantly improve the convergence bound of gradient descent, contrasting with the acceleration phenomenon occurring in the strongly…

Optimization and Control · Mathematics 2026-02-11 Julien Hermant

An appealing property of the natural gradient is that it is invariant to arbitrary differentiable reparameterizations of the model. However, this invariance property requires infinitesimal steps and is lost in practical implementations with…

Machine Learning · Computer Science 2018-06-11 Yang Song , Jiaming Song , Stefano Ermon

This article derives lower bounds on the convergence rate of continuous-time gradient-based optimization algorithms. The algorithms are subjected to a time-normalization constraint that avoids a reparametrization of time in order to make…

Optimization and Control · Mathematics 2020-08-04 Michael Muehlebach , Michael I. Jordan

We study a class of optimization problems including matrix scaling, matrix balancing, multidimensional array scaling, operator scaling, and tensor scaling that arise frequently in theory and in practice. Some of these problems, such as…

Computational Complexity · Computer Science 2024-11-19 Cole Franks , Philipp Reichenbach

We present a method for solving general nonconvex-strongly-convex bilevel optimization problems. Our method -- the \emph{Restarted Accelerated HyperGradient Descent} (\texttt{RAHGD}) method -- finds an $\epsilon$-first-order stationary…

Optimization and Control · Mathematics 2023-07-04 Haikuo Yang , Luo Luo , Chris Junchi Li , Michael I. Jordan

Non-convex optimization problems are ubiquitous in machine learning, especially in Deep Learning. While such complex problems can often be successfully optimized in practice by using stochastic gradient descent (SGD), theoretical analysis…

Machine Learning · Computer Science 2022-02-21 Harsh Vardhan , Sebastian U. Stich