papers

Publications (49)

math.ST2026

Aggregation with Exponential Weights is Optimal in Expectation

Mikael Møller Høgsgaard, Patrick Rebeschini, Tobias Wegel

The aggregation with exponential weights (AEW) estimator is not fully understood in the basic setting of model selection aggregation with squared loss. In particular, whether it is…

cs.LG2023

Linear Convergence for Natural Policy Gradient with Log-linear Policy Parametrization

Carlo Alfano, Patrick Rebeschini

We analyze the convergence rate of the unregularized natural policy gradient algorithm with log-linear policy parametrizations in infinite-horizon discounted Markov decision proces…

math.ST2015

Can local particle filters beat the curse of dimensionality?

Patrick Rebeschini, Ramon van Handel

The discovery of particle filtering methods has enabled the use of nonlinear filtering in a wide array of applications. Unfortunately, the approximation error of particle filters t…

math.PR2013

Comparison Theorems for Gibbs Measures

Patrick Rebeschini, Ramon van Handel

The Dobrushin comparison theorem is a powerful tool to bound the difference between the marginals of high-dimensional probability distributions in terms of their local specificatio…

stat.ML2015

Fast Mixing for Discrete Point Processes

Patrick Rebeschini, Amin Karbasi

We investigate the systematic mechanism for designing fast mixing Markov chain Monte Carlo algorithms to sample from discrete point processes under the Dobrushin uniqueness conditi…

stat.ML2023

Generalization Bounds for Label Noise Stochastic Gradient Descent

Jung Eun Huh, Patrick Rebeschini

We develop generalization error bounds for stochastic gradient descent (SGD) with label noise in non-convex settings under uniform dissipativity and smoothness conditions. Under a…