255 citations · 2.4k across the 127 of their papers we have counts for
6 papers · 2 filters
An Adaptive Algorithm for Finite Stochastic Partial Monitoring
Gabor Bartok, Navid Zolghadr, Csaba Szepesvari
We present a new anytime algorithm that achieves near-optimal regret for any instance of finite stochastic partial monitoring. In particular, the new algorithm achieves the minimax…
Statistical Linear Estimation with Penalized Estimators: an Application to Reinforcement Learning
Bernardo Avila Pires, Csaba Szepesvari
Motivated by value function estimation in reinforcement learning, we study statistical linear inverse problems, i.e., problems where the coefficients of a linear system to be solve…
Apprenticeship Learning using Inverse Reinforcement Learning and Gradient Methods
Gergely Neu, Csaba Szepesvari
In this paper we propose a novel gradient algorithm to learn a policy from an expert's observed behavior assuming that the expert behaves optimally with respect to some unknown rew…
Analysis of Kernel Mean Matching under Covariate Shift
Yaoliang Yu, Csaba Szepesvari
In real supervised learning scenarios, it is not uncommon that the training and test sample follow different probability distributions, thus rendering the necessity to correct the…
A Randomized Mirror Descent Algorithm for Large Scale Multiple Kernel Learning
Arash Afkanpour, András György, Csaba Szepesvári +1
We consider the problem of simultaneously learning to linearly combine a very large number of kernels and learn a good predictor based on the learnt kernel. When the number of kern…
PAC-Bayesian Policy Evaluation for Reinforcement Learning
Mahdi MIlani Fard, Joelle Pineau, Csaba Szepesvari
Bayesian priors offer a compact yet general means of incorporating domain knowledge into many learning tasks. The correctness of the Bayesian analysis and inference, however, large…