Identity testing for Mallows model

no code implementations • NeurIPS 2021 • Róbert Busa-Fekete, Dimitris Fotakis, Balazs Szorenyi, Emmanouil Zampetakis

In this paper, we devise identity tests for ranking data that is generated from Mallows model both in the \emph{asymptotic} and \emph{non-asymptotic} settings.

A Tale of Two-Timescale Reinforcement Learning with the Tightest Finite-Time Bound

no code implementations • 20 Nov 2019 • Gal Dalal, Balazs Szorenyi, Gugan Thoppe

Algorithms such as these have two iterates, $\theta_n$ and $w_n,$ which are updated using two distinct stepsize sequences, $\alpha_n$ and $\beta_n,$ respectively.

reinforcement-learning Reinforcement Learning (RL)

Learning to Crawl

no code implementations • 29 May 2019 • Utkarsh Upadhyay, Robert Busa-Fekete, Wojciech Kotlowski, David Pal, Balazs Szorenyi

Web crawling is the problem of keeping a cache of webpages fresh, i. e., having the most recent copy available when a page is requested.

Multi-objective Bandits: Optimizing the Generalized Gini Index

no code implementations • ICML 2017 • Robert Busa-Fekete, Balazs Szorenyi, Paul Weng, Shie Mannor

We study the multi-armed bandit (MAB) problem where the agent receives a vectorial feedback that encodes many possibly competing objectives to be optimized.

Finite Sample Analysis of Two-Timescale Stochastic Approximation with Applications to Reinforcement Learning

no code implementations • 15 Mar 2017 • Gal Dalal, Balazs Szorenyi, Gugan Thoppe, Shie Mannor

Using this, we provide a concentration bound, which is the first such result for a two-timescale SA.

reinforcement-learning Reinforcement Learning (RL)

Distributed Clustering of Linear Bandits in Peer to Peer Networks

no code implementations • 26 Apr 2016 • Nathan Korda, Balazs Szorenyi, Shuai Li

We provide two distributed confidence ball algorithms for solving linear bandit problems in peer to peer networks with limited communication capabilities.

Clustering