Person: Csaba Szepesvári

DBLP: Szepesv=aacute=ri:Csaba

Contributed to:

2015

2014

2014

2013

2013

2012

2010

2009

2008

2007

2005

2004

1998

1996

Wrote 24 papers:

ICML-2015-HuangGS #analysis #component #independence

Deterministic Independent Component Analysis (RH, AG, CS), pp. 2521–2530.

ICML-2015-KvetonSWA #learning #rank

Cascading Bandits: Learning to Rank in the Cascade Model (BK, CS, ZW, AA), pp. 767–776.

ICML-2015-WuGS #combinator #feedback #finite #identification #on the

On Identifying Good Options under Combinatorially Structured Feedback in Finite Noisy Environments (YW, AG, CS), pp. 1283–1291.

ICML-c1-2014-DickGS #learning #markov #online #process #sequence

Online Learning in Markov Decision Processes with Changing Cost Sequences (TD, AG, CS), pp. 512–520.

ICML-c2-2014-NeufeldGSS #adaptation #monte carlo

Adaptive Monte Carlo via Bandit Allocation (JN, AG, CS, DS), pp. 1944–1952.

ICML-c1-2013-AfkanpourGSB #algorithm #kernel #learning #multi #random #scalability

A Randomized Mirror Descent Algorithm for Large Scale Multiple Kernel Learning (AA, AG, CS, MB), pp. 374–382.

ICML-c1-2013-YuCSS #theorem

Characterizing the Representer Theorem (YY, HC, DS, CS), pp. 570–578.

ICML-c3-2013-JoulaniGS #feedback #learning #online

Online Learning under Delayed Feedback (PJ, AG, CS), pp. 1453–1461.

ICML-c3-2013-PiresSG #bound #classification #multi

Cost-sensitive Multiclass Classification Risk Bounds (BAP, CS, MG), pp. 1391–1399.

ICML-2012-BartokZS #adaptation #algorithm #finite #monitoring #probability

An adaptive algorithm for finite stochastic partial monitoring (GB, NZ, CS), p. 231.

ICML-2012-PiresS #estimation #learning #linear #statistics

Statistical linear estimation with penalized estimators: an application to reinforcement learning (BAP, CS), p. 228.

ICML-2012-YuS #analysis #kernel

Analysis of Kernel Mean Matching under Covariate Shift (YY, CS), p. 150.

ICML-2010-LiPSG #learning #parametricity

Budgeted Distribution Learning of Belief Net Parameters (LL, BP, CS, RG), pp. 879–886.

ICML-2010-MaeiSBS #approximate #learning #towards

Toward Off-Policy Learning Control with Function Approximation (HRM, CS, SB, RSS), pp. 719–726.

ICML-2010-SzitaS #bound #complexity #learning #modelling

Model-based reinforcement learning with nearly tight exploration complexity bounds (IS, CS), pp. 1031–1038.

ICML-2009-FarhangfarGS #image #learning

Learning to segment from a few well-selected training images (AF, RG, CS), pp. 305–312.

ICML-2009-PoczosASGS #exclamation #learning

Learning when to stop thinking and do something! (BP, YAY, CS, RG, NRS), pp. 825–832.

ICML-2009-SuttonMPBSSW #approximate #learning #linear #performance

Fast gradient-descent methods for temporal-difference learning with linear function approximation (RSS, HRM, DP, SB, DS, CS, EW), pp. 993–1000.

ICML-2008-MnihSA #empirical

Empirical Bernstein stopping (VM, CS, JYA), pp. 672–679.

ICML-2007-FarahmandSA #adaptation #estimation

Manifold-adaptive dimension estimation (AMF, CS, JYA), pp. 265–272.

ICML-2005-SzepesvariM #bound #finite

Finite time bounds for sampling based fitted value iteration (CS, RM), pp. 880–887.

ICML-2004-SzepesvariS

Interpolation-based Q-learning (CS, WDS).

ICML-1998-GaborKS #learning #multi

Multi-criteria Reinforcement Learning (ZG, ZK, CS), pp. 197–205.

ICML-1996-LittmanS #convergence

A Generalized Reinforcement-Learning Model: Convergence and Applications (MLL, CS), pp. 310–318.