Multiclass Boosting and the Cost of Weak Learning

no code implementations • NeurIPS 2021 • Nataly Brukhim, Elad Hazan, Shay Moran, Indraneel Mukherjee, Robert E. Schapire

Here, we focus on an especially natural formulation in which the weak hypotheses are assumed to belong to an ''easy-to-learn'' base class, and the weak learner is an agnostic PAC learner for that class with respect to the standard classification loss.

Relative Performance Guarantees for Approximate Inference in Latent Dirichlet Allocation

no code implementations • NeurIPS 2008 • Indraneel Mukherjee, David M. Blei

In this paper we provide the beginnings of such understanding.

Variational Inference