R. L. Kar

Publication List Details

Period

2007 - 2008

Number

2

Co-Authors

Probably approximately correct learning with beta mixing input sequences,” private communication (2008)

R. L. Kar, M. Vidyasagar

Abstract. In this paper, we study the behaviour of PAC learning algorithms when the input sequence is not i.i.d., but is β-mixing instead. A meta-theorem is proved, showing that if an algorithm is...

Markov Property and Ergodicity of the Nonlinear A.G. Bhatt ∗ Indian Statistical Institute, New Delhi Filter (2007)

R. L. Kar, A. Budhiraja

In this paper we first prove, under quite general conditions, that the nonlinear filter and the pair: (signal,filter) are Feller-Markov processes. The state space of the signal is allowed to be non...