We extend the well-known BFGS quasi-Newton method and its memory-limited variant LBFGS to the optimization of nonsmooth convex objectives. This is done in a rigorous fashion by ge...
This paper presents a novel method for illuminationinvariant and contrast preserving feature extraction, aimed at improving performance of tracking under complex light condition. ...
Pareto surfaces in the performance space determine the range of feasible performance values for a circuit topology in a given technology. We present a non-dominated sorting based ...
Saurabh K. Tiwary, Pragati K. Tiwary, Rob A. Ruten...
An image mosaics algorithm based on improved phase correlation is proposed in this paper. The improved phase correlation improves on the conventional phase correlation in three asp...
L1 regularized logistic regression is now a workhorse of machine learning: it is widely used for many classification problems, particularly ones with many features. L1 regularized...
Su-In Lee, Honglak Lee, Pieter Abbeel, Andrew Y. N...