Best of NIPS 2012

Next Wednesday, the 9/2, we will have a group covering some of the work presented this year at NIPS. Each one should pick one paper and share with the group (about 15 minutes).
To make sure we don’t all pick the same paper, please comment on this post with your selection.
All papers are up for grabs, so start looking for your fav!

Online Passive-Aggressive Algorithms

This week we will cover the paper –
Online Passive-Aggressive Algorithms
by Crammer et al. This group will be especially interesting thanks to Koby who has kindly agreed to share some insights into this work.

Abstract
We present a family of margin based online learning algorithms for various prediction tasks. In particular we derive and analyze algorithms for binary and multiclass categorization, regression, uniclass prediction and sequence prediction. The update steps of our different algorithms are all based on analytical solutions to simple constrained optimization problems. This unified view allows us to prove worst-case loss bounds for the different algorithms and for the various decision problems based on a single lemma. Our bounds on the cumulative loss of the algorithms are relative to the smallest loss that can be attained by any fixed hypothesis, and as such are applicable to both realizable and unrealizable settings. We demonstrate some of the merits of the proposed algorithms in a series of experiments with synthetic and real data sets.

We have moved the time back to 9:30.

See you on Wednesday (2/1/2012)!