English
Related papers

Related papers: Kurdyka-{\L}ojasiewicz exponent via inf-projection

200 papers

A critical challenge inherent to the projection method applied to the Landau-Lifshitz equation is the deficiency of rigorous theoretical justifications for the stability of its projection step. To mitigate this limitation, we introduce a…

Numerical Analysis · Mathematics 2026-02-16 Changjian Xie

Potential functions in highly pertinent applications, such as deep learning in over-parameterized regime, are empirically observed to admit non-isolated minima. To understand the convergence behavior of stochastic dynamics in such…

Probability · Mathematics 2025-02-20 Yun Gong , Niao He , Zebang Shen

Counterexamples to some old-standing optimization problems in the smooth convex coercive setting are provided. We show that block-coordinate, steepest descent with exact search or Bregman descent methods do not generally converge. Other…

Optimization and Control · Mathematics 2020-01-30 Jerome Bolte , Edouard Pauwels

Kullback-Leibler divergence (KL) regularization is widely used in reinforcement learning, but it becomes infinite under support mismatch and can degenerate in low-noise limits. Utilizing a unified information-geometric framework, we…

Optimization and Control · Mathematics 2026-02-03 Viktor Stein , Adwait Datar , Nihat Ay

Let K be a complete, algebraically closed nonarchimedean valued field, and let f(z) in K(z) be a rational function of degree d at least 2. We give an algorithm to determine whether f(z) has potential good reduction over K, based on a…

Dynamical Systems · Mathematics 2013-04-08 Robert Rumely

Three decades ago, Stanley and Brenti initiated the study of the Kazhdan--Lusztig--Stanley (KLS) functions, putting on common ground several polynomials appearing in algebraic combinatorics, discrete geometry, and representation theory. In…

Combinatorics · Mathematics 2026-05-06 Luis Ferroni , Jacob P. Matherne , Lorenzo Vecchi

Continual learning (CL) aims to train models that can learn a sequence of tasks without forgetting previously acquired knowledge. A core challenge in CL is balancing stability -- preserving performance on old tasks -- and plasticity --…

Machine Learning · Computer Science 2025-05-14 Zhenrong Liu , Janne M. J. Huttunen , Mikko Honkala

Minimization of a smooth function on a sphere or, more generally, on a smooth manifold, is the simplest non-convex optimization problem. It has a lot of applications. Our goal is to propose a version of the gradient projection algorithm for…

Optimization and Control · Mathematics 2019-06-28 Maxim Balashov , Boris Polyak , Andrey Tremba

This paper is devoted to developing the alternating minimization algorithm for problems of structured nonconvex optimization proposed by Attouch, Bolt\'e, Redont, and Soubeyran in 2010. Our main result provides significant improvements of…

Optimization and Control · Mathematics 2026-02-02 Glaydston C. Bento , Boris S. Mordukhovich , Tiago S. Mota , Antoine Soubeyran

Structured reinforcement learning and stochastic optimization often involve parameters evolving on matrix Lie groups such as rotations and rigid-body transformations. We establish a representation-optimization dichotomy for…

Optimization and Control · Mathematics 2026-03-27 Sooraj KC , Vivek Mishra

In this paper, we consider a class of structured nonconvex nonsmooth optimization problems, in which the objective function is formed by the sum of a possibly nonsmooth nonconvex function and a differentiable function whose gradient is…

Optimization and Control · Mathematics 2024-10-01 Tan Nhat Pham , Minh N. Dao , Rakibuzzaman Shah , Nargiz Sultanova , Guoyin Li , Syed Islam

In the Euclidean setting, the proximal gradient method and its accelerated variants are a class of efficient algorithms for optimization problems with decomposable objective. In this paper, we develop a Riemannian proximal gradient method…

Optimization and Control · Mathematics 2021-06-01 Wen Huang , Ke Wei

We investigate the robustness of the Frank-Wolfe method when gradients are computed inexactly and examine the relative computational cost of the linear minimization oracle (LMO) versus projection. For smooth nonconvex functions, we…

Optimization and Control · Mathematics 2026-01-27 Tao Hu

In this paper, we study a family of non-convex and possibly non-smooth inf-projection minimization problems, where the target objective function is equal to minimization of a joint function over another variable. This problem include…

Machine Learning · Computer Science 2020-07-15 Yan Yan , Yi Xu , Lijun Zhang , Xiaoyu Wang , Tianbao Yang

This paper concerns a class of constrained optimization problems in which, the objective and constraint functions are both upper-$\mathcal{C}^2$. For such nonconvex and nonsmooth optimization problems, we develop an inexact moving balls…

Optimization and Control · Mathematics 2025-11-14 Ruyu Liu , Shaohua Pan

We study various regularization operators on plurisubharmonic functions that preserve Lelong classes with growth given by certain compact convex sets. The purpose is to show that the weighted Siciak-Zakharyuta functions associated with…

Complex Variables · Mathematics 2026-01-21 Bergur Snorrason

It is proposed to revisit the inverse problem associated with Smoluchowski's coagulation equation. The objective is to reconstruct the functional form of the collision kernel from observations of the time evolution of the cluster size…

Statistical Mechanics · Physics 2015-05-27 Colm Connaughton , Peter P. Jones

The Polyak-{\L}ojasiewicz (P{\L}) inequality extends the favorable optimization properties of strongly convex functions to a broader class of functions. In this paper, we prove a theorem (also obtained by Criscitiello, Rebjock and Boumal in…

Optimization and Control · Mathematics 2026-01-19 Aziz Ben Nejma

The LogSumExp function, dual to the Kullback-Leibler (KL) divergence, plays a central role in many important optimization problems, including entropy-regularized optimal transport (OT) and distributionally robust optimization (DRO). In…

Optimization and Control · Mathematics 2026-02-04 Egor Gladin , Alexey Kroshnin , Jia-Jie Zhu , Pavel Dvurechensky

As a popular Deep Reinforcement Learning (DRL) algorithm, Proximal Policy Optimization (PPO) has demonstrated remarkable efficacy in numerous complex tasks. According to the penalty mechanism in a surrogate, PPO can be classified into PPO…

Machine Learning · Computer Science 2024-10-30 Yunxiao Guo , Han Long , Xiaojun Duan , Kaiyuan Feng , Maochu Li , Xiaying Ma