@inproceedings{desai-etal-2019-evaluating,
title = "Evaluating Lottery Tickets Under Distributional Shifts",
author = "Desai, Shrey and
Zhan, Hongyuan and
Aly, Ahmed",
editor = "Cherry, Colin and
Durrett, Greg and
Foster, George and
Haffari, Reza and
Khadivi, Shahram and
Peng, Nanyun and
Ren, Xiang and
Swayamdipta, Swabha",
booktitle = "Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-6117",
doi = "10.18653/v1/D19-6117",
pages = "153--162",
abstract = "The Lottery Ticket Hypothesis suggests large, over-parameterized neural networks consist of small, sparse subnetworks that can be trained in isolation to reach a similar (or better) test accuracy. However, the initialization and generalizability of the obtained sparse subnetworks have been recently called into question. Our work focuses on evaluating the initialization of sparse subnetworks under distributional shifts. Specifically, we investigate the extent to which a sparse subnetwork obtained in a source domain can be re-trained in isolation in a dissimilar, target domain. In addition, we examine the effects of different initialization strategies at transfer-time. Our experiments show that sparse subnetworks obtained through lottery ticket training do not simply overfit to particular domains, but rather reflect an inductive bias of deep neural networks that can be exploited in multiple domains.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="desai-etal-2019-evaluating">
<titleInfo>
<title>Evaluating Lottery Tickets Under Distributional Shifts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shrey</namePart>
<namePart type="family">Desai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongyuan</namePart>
<namePart type="family">Zhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Aly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Colin</namePart>
<namePart type="family">Cherry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Greg</namePart>
<namePart type="family">Durrett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Foster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shahram</namePart>
<namePart type="family">Khadivi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nanyun</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swabha</namePart>
<namePart type="family">Swayamdipta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The Lottery Ticket Hypothesis suggests large, over-parameterized neural networks consist of small, sparse subnetworks that can be trained in isolation to reach a similar (or better) test accuracy. However, the initialization and generalizability of the obtained sparse subnetworks have been recently called into question. Our work focuses on evaluating the initialization of sparse subnetworks under distributional shifts. Specifically, we investigate the extent to which a sparse subnetwork obtained in a source domain can be re-trained in isolation in a dissimilar, target domain. In addition, we examine the effects of different initialization strategies at transfer-time. Our experiments show that sparse subnetworks obtained through lottery ticket training do not simply overfit to particular domains, but rather reflect an inductive bias of deep neural networks that can be exploited in multiple domains.</abstract>
<identifier type="citekey">desai-etal-2019-evaluating</identifier>
<identifier type="doi">10.18653/v1/D19-6117</identifier>
<location>
<url>https://aclanthology.org/D19-6117</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>153</start>
<end>162</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Lottery Tickets Under Distributional Shifts
%A Desai, Shrey
%A Zhan, Hongyuan
%A Aly, Ahmed
%Y Cherry, Colin
%Y Durrett, Greg
%Y Foster, George
%Y Haffari, Reza
%Y Khadivi, Shahram
%Y Peng, Nanyun
%Y Ren, Xiang
%Y Swayamdipta, Swabha
%S Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F desai-etal-2019-evaluating
%X The Lottery Ticket Hypothesis suggests large, over-parameterized neural networks consist of small, sparse subnetworks that can be trained in isolation to reach a similar (or better) test accuracy. However, the initialization and generalizability of the obtained sparse subnetworks have been recently called into question. Our work focuses on evaluating the initialization of sparse subnetworks under distributional shifts. Specifically, we investigate the extent to which a sparse subnetwork obtained in a source domain can be re-trained in isolation in a dissimilar, target domain. In addition, we examine the effects of different initialization strategies at transfer-time. Our experiments show that sparse subnetworks obtained through lottery ticket training do not simply overfit to particular domains, but rather reflect an inductive bias of deep neural networks that can be exploited in multiple domains.
%R 10.18653/v1/D19-6117
%U https://aclanthology.org/D19-6117
%U https://doi.org/10.18653/v1/D19-6117
%P 153-162
Markdown (Informal)
[Evaluating Lottery Tickets Under Distributional Shifts](https://aclanthology.org/D19-6117) (Desai et al., 2019)
ACL
- Shrey Desai, Hongyuan Zhan, and Ahmed Aly. 2019. Evaluating Lottery Tickets Under Distributional Shifts. In Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019), pages 153–162, Hong Kong, China. Association for Computational Linguistics.