Skip to content

Balzs Szrnyi

Publication record assembled from the DBLP archive of ranked conferences.

Papers indexed

23

Venues

7

Active years

2000–2020

Best venue rank

A*

Where they publish

Papers

23 indexed papers, newest first.

YearVenueTitleAuthors
2020AAAIA Tale of Two-Timescale Reinforcement Learning with the Tightest Finite-Time Bound.Gal Dalal, Balzs Szrnyi, Gugan Thoppe
2020AAAILearning to Crawl.Utkarsh Upadhyay, Rbert Busa-Fekete, Wojciech Kotlowski, Dvid Pl, Balzs Szrnyi
2019COLTOptimal Learning of Mallows Block Model.Rbert Busa-Fekete, Dimitris Fotakis, Balzs Szrnyi, Manolis Zampetakis
2019ICMLBandit Multiclass Linear Classification: Efficient Algorithms for the Separable Case.Alina Beygelzimer, Dvid Pl, Balzs Szrnyi, Devanathan Thiruvenkatachari, Chen-Yu Wei, Chicheng Zhang
2019ICMLThe information-theoretic value of unlabeled data in semi-supervised learning.Alexander Golovnev, Dvid Pl, Balzs Szrnyi
2018AAAIFinite Sample Analyses for TD(0) With Function Approximation.Gal Dalal, Balzs Szrnyi, Gugan Thoppe, Shie Mannor
2018COLTFinite Sample Analysis of Two-Timescale Stochastic Approximation with Applications to Reinforcement Learning.Gal Dalal, Gugan Thoppe, Balzs Szrnyi, Shie Mannor
2018ISAIMPAC Bandits with Risk Constraints.Yahel David, Balzs Szrnyi, Mohammad Ghavamzadeh, Shie Mannor, Nahum Shimkin
2017ICMLMulti-objective Bandits: Optimizing the Generalized Gini Index.Rbert Busa-Fekete, Balzs Szrnyi, Paul Weng, Shie Mannor
2016ICMLDistributed Clustering of Linear Bandits in Peer to Peer Networks.Nathan Korda, Balzs Szrnyi, Shuai Li
2015ICMLQualitative Multi-Armed Bandits: A Quantile-Based Approach.Balzs Szrnyi, Rbert Busa-Fekete, Paul Weng, Eyke Hllermeier
2014AAAIPAC Rank Elicitation through Adaptive Sampling of Stochastic Pairwise Preferences.Rbert Busa-Fekete, Balzs Szrnyi, Eyke Hllermeier
2014ICMLPreference-Based Rank Elicitation using Statistical Models: The Case of Mallows.Rbert Busa-Fekete, Eyke Hllermeier, Balzs Szrnyi
2013ICMLTop-k Selection based on Adaptive Sampling of Noisy Preferences.Rbert Busa-Fekete, Balzs Szrnyi, Weiwei Cheng, Paul Weng, Eyke Hllermeier
2013ICMLGossip-based distributed stochastic bandit algorithms.Balzs Szrnyi, Rbert Busa-Fekete, Istvn Hegeds, Rbert Ormndi, Mrk Jelasity, Balzs Kgl
2013STACSUnlabeled Data Does Provably Help.Malte Darnstdt, Hans Ulrich Simon, Balzs Szrnyi
2012KRHorn Belief Contraction: Remainders, Envelopes and Complexity.Kira V. Adaricheva, Robert H. Sloan, Balzs Szrnyi, Gyrgy Turn
2011ALTSupervised Learning and Co-training.Malte Darnstdt, Hans Ulrich Simon, Balzs Szrnyi
2009ALTCharacterizing Statistical Query Learning: Simplified Notions and Proofs.Balzs Szrnyi
2008AAAIHorn Complements: Towards Horn-to-Horn Belief Revision.Marina Langlois, Robert H. Sloan, Balzs Szrnyi, Gyrgy Turn
2004ALTNew Revision Algorithms.Judy Goldsmith, Robert H. Sloan, Balzs Szrnyi, Gyrgy Turn
2003COLTProjective DNF Formulae and Their Revision.Robert H. Sloan, Balzs Szrnyi, Gyrgy Turn
2000COLTImproved Algorithms for Theory Revision with Queries.Judy Goldsmith, Robert H. Sloan, Balzs Szrnyi, Gyrgy Turn