Timezone: »

Learning SMaLL Predictors
Vikas Garg · Ofer Dekel · Lin Xiao

Thu Dec 06 02:00 PM -- 04:00 PM (PST) @ Room 210 #98

We introduce a new framework for learning in severely resource-constrained settings. Our technique delicately amalgamates the representational richness of multiple linear predictors with the sparsity of Boolean relaxations, and thereby yields classifiers that are compact, interpretable, and accurate. We provide a rigorous formalism of the learning problem, and establish fast convergence of the ensuing algorithm via relaxation to a minimax saddle point objective. We supplement the theoretical foundations of our work with an extensive empirical evaluation.

Author Information

Vikas Garg (MIT)
Ofer Dekel (Microsoft Research)
Lin Xiao (Microsoft Research)

More from the Same Authors