174 citations · 991 across the 46 of their papers we have counts for
Showing 2015Show all
3 papers · 1 filter
cs.GT2015★ 1 cited
Rate of Price Discovery in Iterative Combinatorial Auctions
Jacob Abernethy, Sébastien Lahaie, Matus Telgarsky
We study a class of iterative combinatorial auctions which can be viewed as subgradient descent methods for the problem of pricing bundles to balance supply and demand. We provide…
cs.LG2015★ 126 cited
Representation Benefits of Deep Feedforward Networks
Matus Telgarsky
This note provides a family of classification problems, indexed by a positive integer , where all shallow networks with fewer than exponentially (in ) many nodes exhibit erro…
cs.LG2015★ 6 cited
Convex Risk Minimization and Conditional Probability Estimation
Matus Telgarsky, Miroslav Dudík, Robert Schapire
This paper proves, in very general settings, that convex risk minimization is a procedure to select a unique conditional probability model determined by the classification problem.…