We present a kernel-based recursive least-squares (KRLS) algorithm on a fixed memory budget, capable of recursively learning a nonlinear mapping and tracking changes over time. I...
We introduce and analyze a natural algorithm for multi-venue exploration from censored data, which is motivated by the Dark Pool Problem of modern quantitative finance. We prove t...
Kuzman Ganchev, Yuriy Nevmyvaka, Michael Kearns, J...
Abstract--Recently Kutin and Niyogi investigated several notions of algorithmic stability--a property of a learning map conceptually similar to continuity--showing that training-st...
This paper presents a toolkit for spreadsheet visualization based on logical areas, semantic classes and data Logical areas, semantic classes and data modules are abstract represe...
We present a convex formulation of dictionary learning for sparse signal decomposition. Convexity is obtained by replacing the usual explicit upper bound on the dictionary size by...