Timezone: »

 
Poster
Decoupling "when to update" from "how to update"
Eran Malach · Shai Shalev-Shwartz

Mon Dec 04 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #124
in Posters Mon »

Deep learning requires data. A useful approach to obtain data is to be creative and mine data from various sources, that were created for different purposes. Unfortunately, this approach often leads to noisy labels. In this paper, we propose a meta algorithm for tackling the noisy labels problem. The key idea is to decouple when to update'' fromhow to update''. We demonstrate the effectiveness of our algorithm by mining data for gender classification by combining the Labeled Faces in the Wild (LFW) face recognition dataset with a textual genderizing service, which leads to a noisy dataset. While our approach is very simple to implement, it leads to state-of-the-art results. We analyze some convergence properties of the proposed algorithm.

Keywords: Supervised Deep Networks · Classification · Missing Data

Author Information

Eran Malach (Hebrew University Jerusalem Israel)
Shai Shalev-Shwartz (Mobileye & HUJI)

More from the Same Authors