Abstract— Independent subspace analysis (ISA) is a generalization of independent component analysis (ICA), where multidimensional ICA is incorporated with the idea of invariant f...
We describe a novel framework for the design and analysis of online learning algorithms based on the notion of duality in constrained optimization. We cast a sub-family of universa...
Let p be a rational prime and let Φ(X) be a monic irreducible polynomial in Z[X], with nΦ = deg Φ and δΦ = vp(disc Φ). In [13] Montes describes an algorithm for the decomposi...
EM algorithm is a very popular iteration-based method to estimate the parameters of Gaussian Mixture Model from a large observation set. However, in most cases, EM algorithm is no...
We consider the policy search approach to reinforcement learning. We show that if a “baseline distribution” is given (indicating roughly how often we expect a good policy to v...
J. Andrew Bagnell, Sham Kakade, Andrew Y. Ng, Jeff...