activity
20052023
most citedOnline Regret Bounds for Undiscounted Continuous Reinforcement Learning

44 citations · 238 across the 35 of their papers we have counts for

collaborators

38 papers

q-bio.PE2023

Beauty beacon: correlated strategies for the Fisher runaway process

Daniil Ryabko, Angustias Vaca, Prudencio Pazoca

Suppose that females choose males based on attributes that do not signal any genetic quality that is not related to the choice itself. Can being choosy confer selective advantage i…

cs.LG2020

Universal time-series forecasting with mixture predictors

Daniil Ryabko

This book is devoted to the problem of sequential probability forecasting, that is, predicting the probabilities of the next outcome of a growing sequence of observations given the…

stat.ML2019

Clustering piecewise stationary processes

Azadeh Khaleghi, Daniil Ryabko

The problem of time-series clustering is considered in the case where each data-point is a sample generated by a piecewise stationary ergodic process. Stationary processes are perh…

math.ST2019★ 21 cited

Asymptotic nonparametric statistical analysis of stationary time series

Daniil Ryabko

Stationarity is a very general, qualitative assumption, that can be assessed on the basis of application specifics. It is thus a rather attractive assumption to base statistical an…

cs.LG2018

Finite-time optimality of Bayesian predictors

Daniil Ryabko

The problem of sequential probability forecasting is considered in the most general setting: a model set C is given, and it is required to predict as well as possible if any of the…

cs.LG2017★ 5 cited

Hypotheses testing on infinite random graphs

Daniil Ryabko

Drawing on some recent results that provide the formalism necessary to definite stationarity for infinite random graphs, this paper initiates the study of statistical and learning…