Karthik Sridharan

Multi-view clustering via canonical correlation analysis

Clustering data in high dimensions is believed to be a hard problem in general. A number of efficient clustering algorithms developed in recent years address this problem by projecting the data into a lower-dimensional subspace, e.g. via Principal Components Analysis (PCA) or random projections, before clustering. Here, we consider constructing such projections using multiple views of the data, via Canonical Correlation Analysis (CCA). Under the assumption that the views are un-correlated given the cluster label, we show that the separation conditions required for the algorithm to be successful are significantly weaker than prior results in the literature. We provide results for mixtures of Gaussians and mixtures of log concave distributions. We also provide empirical support from audio-visual speaker clustering (where we desire the clusters to correspond to speaker ID) and from hierarchical Wikipedia document clustering (where one view is the words in the document and the other is the link structure).

Learning Kernel-Based Halfspaces with the 0-1 Loss

We describe and analyze a new algorithm for agnostically learning kernel-based halfspaces with respect to the 0-1 loss function. Unlike most of the previous formulations, which rely on surrogate convex loss functions (e.g., hinge-loss in support vector machines (SVMs) and log-loss in logistic regression), we provide finite time/sample guarantees with respect to the more natural 0-1 loss function. The proposed algorithm can learn kernel-based halfspaces in worst-case time poly

Identifying Handwritten Text in Mixed Documents

(\exp(L\log(L/\epsilon)))

Empirical Entropy, Minimax Regret and Minimax Risk

, for any distribution, where

A dynamic migration model for self-adaptive genetic algorithms

L

A sampling based approach to facial feature extraction

is a Lipschitz constant (which can be thought of as the reciprocal of the margin), and the learned classifier is worse than the optimal halfspace by at most

On Martingale Extensions of Vapnik–Chervonenkis Theory with Applications to Online Learning

\epsilon

On Semi-Probabilistic universal prediction

. We also prove a hardness result, showing that under a certain cryptographic assumption, no algorithm can learn kernel-based halfspaces in time polynomial in

Learning linear and kernel predictors with the 0-1 loss function

L

Competitive Mixtures of Simple Neurons

.