English
Related papers

Related papers: Global Convergence of the (1+1) Evolution Strategy

200 papers

In this work, we analyze the global convergence property of coordinate gradient descent with random choice of coordinates and stepsizes for non-convex optimization problems. Under generic assumptions, we prove that the algorithm iterate…

Optimization and Control · Mathematics 2022-12-01 Ziang Chen , Yingzhou Li , Jianfeng Lu

Many problems in machine learning and game theory can be formulated as saddle-point problems, for which various first-order methods have been developed and proven efficient in practice. Under the general convex-concave assumption, most…

Machine Learning · Computer Science 2020-06-16 Yuan Gao , Christian Kroer , Donald Goldfarb

The filtering-clustering models, including trend filtering and convex clustering, have become an important source of ideas and modeling tools in machine learning and related fields. The statistical guarantee of optimal solutions in these…

Machine Learning · Statistics 2022-01-26 Nhat Ho , Tianyi Lin , Michael I. Jordan

For a functional $\E$ and a peak selection that picks up a global maximum of $\E$ on varying cones, we study the convergence up to a subsequence to a critical point of the sequence generated by a mountain pass type algorithm. Moreover, by…

Analysis of PDEs · Mathematics 2013-01-09 Christopher Grumiau , Christophe Troestler

Most evolutionary algorithms have parameters, which allow a great flexibility in controlling their behavior and adapting them to new problems. To achieve the best performance, it is often needed to control some of the parameters during…

Neural and Evolutionary Computing · Computer Science 2021-06-07 Maxim Buzdalov , Carola Doerr

Randomly initialized first-order optimization algorithms are the method of choice for solving many high-dimensional nonconvex problems in machine learning, yet general theoretical guarantees cannot rule out convergence to critical points of…

Optimization and Control · Mathematics 2018-09-28 Dar Gilboa , Sam Buchanan , John Wright

Chance-constrained problems involve stochastic components in the constraints which can be violated with a small probability. We investigate the impact of different types of chance constraints on the performance of iterative search…

Neural and Evolutionary Computing · Computer Science 2024-05-30 Saba Sadeghi Ahouei , Jacob de Nobel , Aneta Neumann , Thomas Bäck , Frank Neumann

Learning-to-optimize leverages machine learning to accelerate optimization algorithms. While empirical results show tremendous improvements compared to classical optimization algorithms, theoretical guarantees are mostly lacking, such that…

Machine Learning · Computer Science 2025-06-02 Michael Sucker , Peter Ochs

We present a hybrid algorithm between an evolution strategy and a quasi Newton method. The design is based on the Hessian Estimation Evolution Strategy, which iteratively estimates the inverse square root of the Hessian matrix of the…

Optimization and Control · Mathematics 2025-05-19 Tobias Glasmachers

In the evolutionary computation community, it is widely believed that stagnation impedes convergence in evolutionary algorithms, and that convergence inherently indicates optimality. However, this perspective is misleading. In this study,…

Machine Learning · Computer Science 2026-02-06 Xiaojun Zhou

The possibility to use competitive evolutionary algorithms to generate long-term progress is normally prevented by the convergence on limit cycle dynamics in which the evolving agents keep progressing against their current competitors by…

Neural and Evolutionary Computing · Computer Science 2020-05-26 Luca Simione , Stefano Nolfi

Understanding how the time-complexity of evolutionary algorithms (EAs) depend on their parameter settings and characteristics of fitness landscapes is a fundamental problem in evolutionary computation. Most rigorous results were derived…

Neural and Evolutionary Computing · Computer Science 2016-10-28 Dogan Corus , Duc-Cuong Dang , Anton V. Eremeev , Per Kristian Lehre

In this paper, we study the gradient descent-ascent method for convex-concave saddle-point problems. We derive a new non-asymptotic global convergence rate in terms of distance to the solution set by using the semidefinite programming…

Optimization and Control · Mathematics 2022-09-19 Moslem Zamani , Hadi Abbaszadehpeivasti , Etienne de Klerk

Infinite population models are important tools for studying population dynamics of evolutionary algorithms. They describe how the distributions of populations change between consecutive generations. In general, infinite population models…

Neural and Evolutionary Computing · Computer Science 2015-09-29 Bo Song , Victor O. K. Li

We introduce a novel approach for discriminative classification using evolutionary algorithms. We first propose an algorithm to optimize the total loss value using a modified 0-1 loss function in a one-dimensional space for classification.…

Neural and Evolutionary Computing · Computer Science 2018-04-27 Mohammad Reza Bonyadi , David C. Reutens

Efficient global optimization is the problem of minimizing an unknown function f, using as few evaluations f(x) as possible. It can be considered as a continuum-armed bandit problem, with noiseless data and simple regret. Expected…

Machine Learning · Statistics 2013-02-19 Adam D. Bull

Gradient-based first-order convex optimization algorithms find widespread applicability in a variety of domains, including machine learning tasks. Motivated by the recent advances in fixed-time stability theory of continuous-time dynamical…

Machine Learning · Computer Science 2023-10-24 Mayank Baranwal , Param Budhraja , Vishal Raj , Ashish R. Hota

Policy gradient (PG) methods are a widely used reinforcement learning methodology in many applications such as video games, autonomous driving, and robotics. In spite of its empirical success, a rigorous understanding of the global…

Optimization and Control · Mathematics 2020-06-30 Kaiqing Zhang , Alec Koppel , Hao Zhu , Tamer Başar

It is known that evolution strategies in continuous domains might not converge in the presence of noise. It is also known that, under mild assumptions, and using an increasing number of resamplings, one can mitigate the effect of additive…

Optimization and Control · Mathematics 2014-04-10 Marie-Liesse Cauwet

Policy gradient methods, where one searches for the policy of interest by maximizing the value functions using first-order information, become increasingly popular for sequential decision making in reinforcement learning, games, and…

Optimization and Control · Mathematics 2023-10-10 Shicong Cen , Yuejie Chi