CaltechAUTHORS
  A Caltech Library Service

Regularized Learning for Domain Adaptation under Label Shifts

Azizzadenesheli, Kamyar and Liu, Anqi and Yang, Fanny and Anandkumar, Animashree (2019) Regularized Learning for Domain Adaptation under Label Shifts. In: Seventh International Conference on Learning Representations (ICLR 2019), 6-9 May 2019, New Orleans, LA. (Submitted) https://resolver.caltech.edu/CaltechAUTHORS:20190327-085824665

[img] PDF - Submitted Version
See Usage Policy.

1519Kb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20190327-085824665

Abstract

We propose Regularized Learning under Label shifts (RLLS), a principled and a practical domain-adaptation algorithm to correct for shifts in the label distribution between a source and a target domain. We first estimate importance weights using labeled source data and unlabeled target data, and then train a classifier on the weighted source samples. We derive a generalization bound for the classifier on the target domain which is independent of the (ambient) data dimensions, and instead only depends on the complexity of the function class. To the best of our knowledge, this is the first generalization bound for the label-shift problem where the labels in the target domain are not available. Based on this bound, we propose a regularized estimator for the small-sample regime which accounts for the uncertainty in the estimated weights. Experiments on the CIFAR-10 and MNIST datasets show that RLLS improves classification accuracy, especially in the low sample and large-shift regimes, compared to previous methods.


Item Type:Conference or Workshop Item (Poster)
Related URLs:
URLURL TypeDescription
http://arxiv.org/abs/1903.09734arXivPoster
https://openreview.net/forum?id=rJl0r3R9KXOrganizationPoster
https://iclr.cc/Conferences/2019/OrganizationConference Website
ORCID:
AuthorORCID
Azizzadenesheli, Kamyar0000-0001-8507-1868
Additional Information:K. Azizzadenesheli is supported in part by NSF Career Award CCF-1254106 and Air Force FA9550-15-1-0221. This research has been conducted when the first author was a visiting researcher at Caltech. Anqi Liu is supported in part by DOLCIT Postdoctoral Fellowship at Caltech and Caltech’s Center for Autonomous Systems and Technologies. Fan Yang is supported by the Institute for Theoretical Studies ETH Zurich and the Dr. Max Rössler and the Walter Haefner Foundation. A. Anandkumar is supported in part by Microsoft Faculty Fellowship, Google faculty award, Adobe grant, NSF Career Award CCF-1254106, and AFOSR YIP FA9550-15-1-0221.
Group:Center for Autonomous Systems and Technologies (CAST)
Funders:
Funding AgencyGrant Number
NSFCCF-1254106
Air Force Office of Scientific Research (AFOSR)FA9550-15-1-0221
Center for Autonomous Systems and TechnologiesUNSPECIFIED
ETH ZurichUNSPECIFIED
Walter Haefner FoundationUNSPECIFIED
Microsoft Faculty FellowshipUNSPECIFIED
Google Faculty Research AwardUNSPECIFIED
AdobeUNSPECIFIED
Subject Keywords:Deep Learning, Domain Adaptation, Label Shift, Importance Weights, Generalization
Record Number:CaltechAUTHORS:20190327-085824665
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20190327-085824665
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:94184
Collection:CaltechAUTHORS
Deposited By: George Porter
Deposited On:28 Mar 2019 15:25
Last Modified:11 Nov 2020 00:57

Repository Staff Only: item control page