Search Results for author:
Found 19 papers, 0 papers with code
Beauty beacon: correlated strategies for the Fisher runaway process
Moreover, after being established in the population, it can sustain costs of over 35\% .
Universal time-series forecasting with mixture predictors
The main subject of this book are such mixture predictors, and the main results demonstrate the universality of this method in a very general probabilistic setting, but also show some of its limitations.
Clustering piecewise stationary processes
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.
Asymptotic nonparametric statistical analysis of stationary time series
It is thus a rather attractive assumption to base statistical analysis on, especially for problems for which less general qualitative assumptions, such as independence or finite memory, clearly fail.
Finite-time optimality of Bayesian predictors
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 measures (environments) in C is chosen to generate the data.
Hypotheses testing on infinite random graphs
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 questions pertaining to these objects.
Independence clustering (without a matrix)
The independence clustering problem is considered in the following formulation: given a set $S$ of random variables, it is required to find the finest partitioning $\{U_1,\dots, U_k\}$ of $S$ into clusters such that the clusters $U_1,\dots, U_k$ are mutually independent.
Universality of Bayesian mixture predictors
In this work it is shown that the minimax asymptotic performance is always attainable, and it is attained by a convex combination of a countably many measures from the set C (a Bayesian mixture).
Things Bayes can't do
In such a case, if there is a predictor that achieves asymptotically vanishing error for any measure in C, then there is a Bayesian predictor that also has this property, and whose prior is concentrated on (a countable subset of) C.
Characterizing predictable classes of processes
A sequence x1,..., xn,... of discrete-valued observations is generated according to some unknown probabilistic law (measure) mu.
Selecting Near-Optimal Approximate State Representations in Reinforcement Learning
We consider a reinforcement learning setting introduced in (Maillard et al., NIPS 2011) where the learner does not have explicit access to the states of the underlying Markov decision process (MDP).
Unsupervised model-free representation learning
Numerous control and learning problems face the situation where sequences of high-dimensional highly dependent data are available but no or little feedback is provided to the learner, which makes any inference rather challenging.
Online Regret Bounds for Undiscounted Continuous Reinforcement Learning
We derive sublinear regret bounds for undiscounted reinforcement learning in continuous state space.
Locating Changes in Highly Dependent Data with Unknown Number of Change Points
The problem of multiple change point estimation is considered for sequences with unknown number of change points.
Reducing statistical time-series problems to binary classification
The algorithms that we construct for solving these problems are based on a new metric between time-series distributions, which can be evaluated using binary classification methods.
Multiple Change Point Estimation in Stationary Ergodic Time Series
Given a heterogeneous time-series sample, the objective is to find points in time (called change points) where the probability distribution generating the data has changed.
Selecting the State-Representation in Reinforcement Learning
Without knowing neither which of the models is the correct one, nor what are the probabilistic characteristics of the resulting MDP, it is required to obtain as much reward as the optimal policy for the correct model (or for the best of the correct models, if there are several).
On the Relation between Realizable and Nonrealizable Cases of the Sequence Prediction Problem
For some of the formalizations we also show that when a solution exists, it can be obtained as a Bayes mixture over a countable subset of $\mathcal C$.
Clustering processes
We show that, for the case of a known number of clusters, consistency can be achieved under the only assumption that the joint distribution of the data is stationary ergodic (no parametric or Markovian assumptions, no assumptions of independence, neither between nor within the samples).
