English
Related papers

Related papers: Theoretical foundation for CMA-ES from information…

200 papers

Classical Fisher-information asymptotics describe the covariance of regular efficient estimators through the local quadratic approximation of the log-likelihood, and thus capture first-order geometry only. In curved models, including…

Statistics Theory · Mathematics 2026-04-15 Malik Amir , Sourangshu Ghosh

Gibbs-ERM learning is a natural idealized model of learning with stochastic optimization algorithms (such as Stochastic Gradient Langevin Dynamics and ---to some extent--- Stochastic Gradient Descent), while it also arises in other…

Machine Learning · Computer Science 2019-02-06 Ilja Kuzborskij , Nicolò Cesa-Bianchi , Csaba Szepesvári

The mutation strength adaptation properties of a multi-recombinative $(\mu/\mu_I, \lambda)$-ES are studied for isotropic mutations. To this end, standard implementations of cumulative step-size adaptation (CSA) and mutative self-adaptation…

Neural and Evolutionary Computing · Computer Science 2024-08-20 Amir Omeradzic , Hans-Georg Beyer

Statistical inference more often than not involves models which are non-linear in the parameters thus leading to non-Gaussian posteriors. Many computational and analytical tools exist that can deal with non-Gaussian distributions, and…

General Relativity and Quantum Cosmology · Physics 2021-01-20 Eileen Giesel , Robert Reischke , Björn Malte Schäfer , Dominic Chia

Recent research in Cooperative Coevolution~(CC) have achieved promising progress in solving large-scale global optimization problems. However, existing CC paradigms have a primary limitation in that they require deep expertise for selecting…

Machine Learning · Computer Science 2025-04-25 Hongshu Guo , Wenjie Qiu , Zeyuan Ma , Xinglin Zhang , Jun Zhang , Yue-Jiao Gong

Estimation of distribution algorithms (EDAs) constitute a new branch of evolutionary optimization algorithms, providing effective and efficient optimization performance in a variety of research areas. Recent studies have proposed new EDAs…

Neural and Evolutionary Computing · Computer Science 2024-07-29 Dae-Won Kim , Song Ko , Bo-Yeong Kang

In the evolutionary computation research community, the performance of most evolutionary algorithms (EAs) depends strongly on their implemented coordinate system. However, the commonly used coordinate system is fixed and not well suited for…

Neural and Evolutionary Computing · Computer Science 2017-03-21 Zhi-Zhong Liu , Yong Wang , Shengxiang Yang , Ke Tang

Expectation-Maximization (EM) algorithm is a widely used iterative algorithm for computing (local) maximum likelihood estimate (MLE). It can be used in an extensive range of problems, including the clustering of data based on the Gaussian…

Machine Learning · Statistics 2023-03-28 Pierre Houdouin , Esa Ollila , Frederic Pascal

Evolution Strategy (ES) algorithms have shown promising results in training complex robotic control policies due to their massive parallelism capability, simple implementation, effective parameter-space exploration, and fast training time.…

Robotics · Computer Science 2022-07-28 Kuang-Huei Lee , Ofir Nachum , Tingnan Zhang , Sergio Guadarrama , Jie Tan , Wenhao Yu

The (1+1)-evolution strategy (ES) with success-based step-size adaptation is analyzed on a general convex quadratic function and its monotone transformation, that is, $f(x) = g((x - x^*)^\mathrm{T} H (x - x^*))$, where…

Neural and Evolutionary Computing · Computer Science 2021-04-13 Daiki Morinaga , Kazuto Fukuchi , Jun Sakuma , Youhei Akimoto

This paper establishes a mathematical foundation for the Adam optimizer, elucidating its connection to natural gradient descent through Riemannian and information geometry. We provide an accessible and detailed analysis of the diagonal…

Machine Learning · Computer Science 2024-09-05 Dongseong Hwang

Natural Evolution Strategies (NES) is a promising framework for black-box continuous optimization problems. NES optimizes the parameters of a probability distribution based on the estimated natural gradient, and one of the key parameters…

Neural and Evolutionary Computing · Computer Science 2022-02-08 Masahiro Nomura , Isao Ono

Data assimilation methods aim at estimating the state of a system by combining observations with a physical model. When sequential data assimilation is considered, the joint distribution of the latent state and the observations is described…

Methodology · Statistics 2018-04-23 Thi Tuyet Trang Chau , Pierre Ailliot , Valérie Monbet , Pierre Tandeo

An interactive stochastics, evaluated by an entropy functional (EF) of a random field and informational process' path functional (IPF), allows us modeling the evolutionary information processes and revealing regularities of evolution…

Information Theory · Computer Science 2011-09-15 Vladimir S. Lerner

Designing evolutionary algorithms capable of uncovering highly evolvable representations is an open challenge; such evolvability is important because it accelerates evolution and enables fast adaptation to changing circumstances. This paper…

Neural and Evolutionary Computing · Computer Science 2019-07-16 Alexander Gajewski , Jeff Clune , Kenneth O. Stanley , Joel Lehman

Masked autoencoders (MAEs) represent a prominent self-supervised learning paradigm in computer vision. Despite their empirical success, the underlying mechanisms of MAEs remain insufficiently understood. Recent studies have attempted to…

Computer Vision and Pattern Recognition · Computer Science 2025-02-28 Tao Huang , Yanxiang Ma , Shan You , Chang Xu

While the expected calibration error (ECE), which employs binning, is widely adopted to evaluate the calibration performance of machine learning models, theoretical understanding of its estimation bias is limited. In this paper, we present…

Machine Learning · Computer Science 2025-05-27 Futoshi Futami , Masahiro Fujisawa

This paper aims at presenting a new application of information geometry to reinforcement learning focusing on dynamic treatment resumes. In a standard framework of reinforcement learning, a Q-function is defined as the conditional…

Methodology · Statistics 2022-11-17 Shinto Eguchi

There has been a recent focus in reinforcement learning on addressing continuous state and action problems by optimizing parameterized policies. PI2 is a recent example of this approach. It combines a derivation from first principles of…

Machine Learning · Computer Science 2012-06-22 Freek Stulp , Olivier Sigaud

This paper presents a new performance bound for estimation problems where the parameter to estimate lies in a Riemannian manifold (a smooth manifold endowed with a Riemannian metric) and follows a given prior distribution. In this setup,…

Statistics Theory · Mathematics 2024-09-10 Florent Bouchard , Alexandre Renaux , Guillaume Ginolhac , Arnaud Breloy