Timezone: »

 
Poster
From Online to Batch Learning with Cutoff-Averaging
Ofer Dekel

Tue Dec 09 07:30 PM -- 12:00 AM (PST) @

We present "cutoff averaging", a technique for converting any conservative online learning algorithm into a batch learning algorithm. Most online-to-batch conversion techniques work well with certain types of online learning algorithms and not with others, whereas cutoff averaging explicitly tries to adapt to the characteristics of the online algorithm being converted. An attractive property of our technique is that it preserves the efficiency of the original online algorithm, making it approporiate for large-scale learning problems. We provide a statistical analysis of our technique and back our theoretical claims with experimental results.

Author Information

Ofer Dekel (Microsoft Research)

More from the Same Authors