We prove new lower bounds for learning intersections of halfspaces, one of the most important concept classes in computational learning theory. Our main result is that any statist...
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...
Abstract Surrogate maximization (or minimization) (SM) algorithms are a family of algorithms that can be regarded as a generalization of expectation-maximization (EM) algorithms. A...
We propose a general-purpose stochastic optimization algorithm, the so-called annealing stochastic approximation Monte Carlo (ASAMC) algorithm, for neural network training. ASAMC c...
Which active learning methods can we expect to yield good performance in learning binary and multi-category logistic regression classifiers? Addressing this question is a natural ...
In many learning problems prior knowledge about pattern variations can be formalized and beneficially incorporated into the analysis system. The corresponding notion of invarianc...
Platt’s probabilistic outputs for Support Vector Machines (Platt, 2000) has been popular for applications that require posterior class probabilities. In this note, we propose an ...
Classifier calibration is the process of converting classifier scores into reliable probability estimates. Recently, a calibration technique based on isotonic regression has gain...