NDLI: Scaling up M-estimation via sampling designs: The Horvitz-Thompson stochastic gradient descent

Content Provider	IEEE Xplore Digital Library
Author	Clemencon, S. Bertail, P. Chautru, E.
Copyright Year	2014
Description	Author affiliation: Lab. AGM, Univ. de Cergy-Pontoise, Cergy-Pontoise, France (Chautru, E.) \|\| LTCI, Telecom ParisTech, Paris, France (Clemencon, S.) \|\| Univ. Paris-Ouest MODAL'X & CREST - INSEE, Paris, France (Bertail, P.)
Abstract	In certain situations that shall be undoubtedly more and more common in the Big Data era, the datasets available are so massive that computing statistics over the full sample is hardly feasible, if not unfeasible. A natural approach in this context consists in using survey schemes and substituting the “full data” statistics with their counterparts based on the resulting random samples, of manageable size. It is the purpose of this paper to investigate the impact of survey sampling with unequal inclusion probabilities on (stochastic) gradient descent-based M-estimation methods in large-scale statistical-learning problems. We prove that, in presence of some a priori information, one may significantly reduce the number of terms that must be averaged to estimate the gradient at each step with overwhelming probability, while preserving the asymptotic accuracy. These striking results are described here by limit theorems.
Starting Page	25
Ending Page	30
File Size	761541
Page Count	6
File Format	PDF
ISBN	9781479956661
DOI	10.1109/BigData.2014.7004208
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2014-10-27
Publisher Place	USA
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Horvitz-Thompson estimation Accuracy Survey Sociology Statistical learning Estimation Probability Big data Stochastic gradient descent Sampling design Statistics Zinc
Content Type	Text
Resource Type	Article

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

ƞPS Sampling Designs and the Horvitz- Thompson estimator

Survey schemes for stochastic gradient descent with applications to M-estimation

Scaling-up Empirical Risk Minimization: Optimization of Incomplete U-statistics

Improved Horvitz-Thompson Estimator in Survey Sampling

BigSurvSGD: Big Survival Data Analysis via Stochastic Gradient Descent

An adaptive algorithm for estimating inclusion probabilities and performing the Horvitz–Thompson criterion in complex designs

An Efficient Algorithm For Generalized Linear Bandit: Online Stochastic Gradient Descent and Thompson Sampling

Optimal Strategies in 2-Stage Sampling

Online Statistical Inference for Contextual Bandits via Stochastic Gradient Descent

Scaling up M-estimation via sampling designs: The Horvitz-Thompson stochastic gradient descent

Similar Documents

ƞPS Sampling Designs and the Horvitz- Thompson estimator

Survey schemes for stochastic gradient descent with applications to M-estimation

Scaling-up Empirical Risk Minimization: Optimization of Incomplete U-statistics

Improved Horvitz-Thompson Estimator in Survey Sampling

BigSurvSGD: Big Survival Data Analysis via Stochastic Gradient Descent

An adaptive algorithm for estimating inclusion probabilities and performing the Horvitz–Thompson criterion in complex designs

An Efficient Algorithm For Generalized Linear Bandit: Online Stochastic Gradient Descent and Thompson Sampling

Optimal Strategies in 2-Stage Sampling

Online Statistical Inference for Contextual Bandits via Stochastic Gradient Descent

Scaling up M-estimation via sampling designs: The Horvitz-Thompson stochastic gradient descent