Black-Box Optimization Using Geodesics in Statistical Manifolds
نویسندگان
چکیده
منابع مشابه
Black-Box Optimization Using Geodesics in Statistical Manifolds
Information geometric optimization (IGO) is a general framework for stochastic optimization problems aiming at limiting the influence of arbitrary parametrization choices: the initial problem is transformed into the optimization of a smooth function on a Riemannian manifold, defining a parametrization-invariant first order differential equation and, thus, yielding an approximately parametrizati...
متن کاملStudies in Continuous Black-box Optimization
O ptimization is the research field that studies that studies the design of algorithms for finding the best solutions to problems we humans throw at them. While the whole domain is of important practical utility, the present thesis will focus on the subfield of continuous black-box optimization, presenting a collection of novel, state-of-the-art algorithms for solving problems in that class. Fi...
متن کاملConsensus for black-box nonlinear agents using optimistic optimization
An important problem in multiagent systems is consensus, which requires the agents to agree on certain controlled variables of interest. We focus on the challenge of dealing in a generic way with nonlinear agent dynamics, represented as a black-box with unknown mathematical form. Our approach designs a reference behavior with a classical consensus method. The main novelty is using optimistic op...
متن کاملConstrained Black Box Optimization with Data Analysis
This paper presents the design of and test results for an algorithm solving constrained black box optimization problems globally using mainly methods from data analysis. A particular focus is put on constraints: in addition to bound constraints, we also handle black box inequality and equality constraints. In particular, our algorithm is able to handle equality constraints given in implicit for...
متن کاملOptimal Black-Box Reductions Between Optimization Objectives
The diverse world of machine learning applications has given rise to a plethora of algorithms and optimization methods, finely tuned to the specific regression or classification task at hand. We reduce the complexity of algorithm design for machine learning by reductions: we develop reductions that take a method developed for one setting and apply it to the entire spectrum of smoothness and str...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Entropy
سال: 2015
ISSN: 1099-4300
DOI: 10.3390/e17010304