activity
20102025
most citedOptimal measures and Markov transition kernels

18 citations · 37 across the 7 of their papers we have counts for

collaborators

8 papers

q-bio.PE2025

Analysis and Optimization of Probabilities of Beneficial Mutation and Crossover Recombination in a Hamming Space

Roman V. Belavkin

Inspired by Fisher's geometric approach to study beneficial mutations, we analyse probabilities of beneficial mutation and crossover recombination of strings in a general Hamming s…

q-fin.ST2024

Value of Information in the Mean-Square Case and its Application to the Analysis of Financial Time-Series Forecast

Roman Belavkin, Panos Pardalos, Jose Principe

The advances and development of various machine learning techniques has lead to practical solutions in various areas of science, engineering, medicine and finance. The great choice…

cs.IT2019★ 5 cited

Relation between the Kantorovich-Wasserstein metric and the Kullback-Leibler divergence

Roman V. Belavkin

We discuss a relation between the Kantorovich-Wasserstein (KW) metric and the Kullback-Leibler (KL) divergence. The former is defined using the optimal transport problem (OTP) in t…

cs.IT2015

Asymmetric Topologies on Statistical Manifolds

Roman V. Belavkin

Asymmetric information distances are used to define asymmetric norms and quasimetrics on the statistical manifold and its dual space of random variables. Quasimetric topology, gene…

math.OC2014★ 4 cited

Asymmetry of Risk and Value of Information

Roman V. Belavkin

The von Neumann and Morgenstern theory postulates that rational choice under uncertainty is equivalent to maximization of expected utility (EU). This view is mathematically appeali…

q-bio.PE2012★ 9 cited

Monotonicity of Fitness Landscapes and Mutation Rate Control

Roman V. Belavkin, Alastair Channon, Elizabeth Aston +3

A common view in evolutionary biology is that mutation rates are minimised. However, studies in combinatorial optimisation and search have shown a clear advantage of using variable…

math.OC2010★ 18 cited

Optimal measures and Markov transition kernels

Roman V. Belavkin

We study optimal solutions to an abstract optimization problem for measures, which is a generalization of classical variational problems in information theory and statistical physi…

cs.GT2010★ 1 cited

Conservation Law of Utility and Equilibria in Non-Zero Sum Games

Roman V. Belavkin

This short note demonstrates how one can define a transformation of a non-zero sum game into a zero sum, so that the optimal mixed strategy achieving equilibrium always exists. The…