Search

Smriti Bhagat

from New York, NY
Age ~44
Get Report
Also known as:
Bhagat Smriti
Related to:
Kokil W Bhagat, 45Pankaj Bhagat
Connected to:
Ahmed M Bhagat, 79Ali M Bhagat, 38Anant S Bhagat, 96Anupdas Bhagat, 45Archana Bhagat, 39Aziz K Bhagat, 42Bhadresh L Bhagat, 58Dishant G Bhagat, 43Divyesh K Bhagat, 53Girish P Bhagat, 63

Smriti Bhagat Phones & Addresses

  • New York, NY
  • San Francisco, CA
  • 211 Walnut St, Highland Park, NJ 08904 (732) 846-6254
  • 76 Adelaide Ave, Highland Park, NJ 08904 (732) 846-6254
  • 209 Raritan Ave, Highland Park, NJ 08904 (732) 448-3463
  • 209 Raritan Ave, Highland Park, NJ 08904

Resumes

Resumes

Smriti Bhagat Photo 1

Data Scientist

View page
Location:
San Francisco, CA
Industry:
Research
Work:
Technicolor Nov 2011 - Oct 2014
Researcher
Facebook Nov 2011 - Oct 2014
Data Scientist
The University of British Columbia Nov 2010 - Nov 2011
Postdoctoral Fellow
Rutgers University Sep 2005 - Sep 2010
Research Assistant
Google May 2007 - Sep 2007
Research Intern
Education:
Rutgers University 2005 - 2010
Doctorates, Doctor of Philosophy, Computer Science Rutgers University 2003 - 2005
Masters, Computer Science Visvesvaraya Technological University 1999 - 2003
Bachelor of Engineering, Bachelors, Computer Science
Smriti Bhagat Photo 2

Smriti Bhagat

View page
Smriti Bhagat Photo 3

Smriti Bhagat

View page
Location:
San Francisco Bay Area
Industry:
Research

Publications

Us Patents

Link-Based Classification Of Graph Nodes

View page
US Patent:
20090132561, May 21, 2009
Filed:
Nov 21, 2007
Appl. No.:
11/943681
Inventors:
Graham Cormode - Summit NJ, US
Smriti Bhagat - Highland Park NJ, US
Irina Rozenbaum - Piscataway NJ, US
Assignee:
AT&T LABS, INC. - Austin TX
International Classification:
G06F 17/30
US Classification:
707100, 707E17089
Abstract:
A method of labeling unlabeled nodes in a graph that represents objects that have an explicit structure between them. A computing device can use a labeling engine to labeled nodes in a graph that are labeled and can identify an unlabeled node in the graph that is structurally associated with the labeled nodes. The labeling engine can label the unlabeled node with the label of the labeled node based on the structural association between the unlabeled node and the labeled node.

Anonymization Of Data Over Multiple Temporal Releases

View page
US Patent:
20120011591, Jan 12, 2012
Filed:
Jul 6, 2010
Appl. No.:
12/830685
Inventors:
Graham Cormode - Morristown NJ, US
Smriti Bhagat - New York NY, US
Balachander Krishnamurthy - New York NY, US
Divesh Srivastava - Summit NJ, US
International Classification:
G06F 21/00
US Classification:
726 26
Abstract:
The present disclosure is directed to systems, methods, and computer-readable storage media for anonymizing data over multiple temporal releases. Data is received, and nodes and connections in the data are identified. The data also is analyzed to identify predicted connections. The nodes, the connections, and the predicted connections are analyzed to determine how to group the nodes in the data. The data is published, and the grouping of the nodes is extended to subsequent temporal releases of the data, the nodes of which are grouped in accordance with the grouping used with the data.

Anonymization Of Data Over Multiple Temporal Releases

View page
US Patent:
20130247214, Sep 19, 2013
Filed:
May 6, 2013
Appl. No.:
13/887588
Inventors:
Smriti Bhagat - San Francisco CA, US
Divesh Srivastava - Summit NJ, US
Assignee:
AT&T Intellectual Property I, L.P - Atlanta GA
International Classification:
G06F 21/62
US Classification:
726 26
Abstract:
The present disclosure is directed to systems, methods, and computer-readable storage media for anonymizing data over multiple temporal releases. Data is received, and nodes and connections in the data are identified. The data also is analyzed to identify predicted connections. The nodes, the connections, and the predicted connections are analyzed to determine how to group the nodes in the data. The data is published, and the grouping of the nodes is extended to subsequent temporal releases of the data, the nodes of which are grouped in accordance with the grouping used with the data.

Privacy Protection Against Curious Recommenders

View page
US Patent:
20150339493, Nov 26, 2015
Filed:
Aug 7, 2013
Appl. No.:
14/652713
Inventors:
Efstratois IOANNIDIS - San Francisco CA, US
Ehud WEINSBERG - Menlo Park CA, US
Smriti BHAGAT - San Francisco CA, US
Nadia FAWAZ - Santa Clara CA, US
Andrea F. MONTANARI - Sunnyvale CA, US
Nina TAFT - San Francisco CA, US
- Issy-Les-Moulineaux, FR
International Classification:
G06F 21/62
Abstract:
A method and apparatus for protecting user privacy in a recommender system are described including determining what information to release to a user for a movie, transmitting the information to the user, accepting obfuscated input from the user and estimating the user's non-private feature vector. Also described are a method and apparatus for protecting user privacy in a recommender system including receiving movie information, accepting a user's movie feedback, accepting user's private information, calculating an obfuscation value and transmitting the obfuscation value.

Proposing Objects To A User To Efficiently Discover Demographics From Item Ratings

View page
US Patent:
20150339687, Nov 26, 2015
Filed:
Dec 12, 2013
Appl. No.:
14/652258
Inventors:
- Issy les Moulineaux, FR
Udi WEINSBERG - Menlo Park CA, US
Smriti BHAGAT - San Francisco CA, US
International Classification:
G06Q 30/02
G06N 99/00
G06N 5/04
G06N 7/00
Abstract:
The current methods and apparatus provide a system that learns a private attribute, such as gender, based on at least one iteration of presenting an item to a user and receiving ratings from the user for this item. In an exemplary embodiment, the system may solicit ratings for strategically selected items, such as movies for example, and then infers the user's gender. Based on the assessed confidence in the demographic selected, the system may repeat the selection, presentation and ratings of another item. The proposed system can strategically select the sequence of items that are presented to the user for a rating. By selecting the next item to be rated based on a maximum posterior probability confidence, a demographic with a certain threshold of confidence can be inferred. The inventive arrangements are based on novel usage of Bayesian matrix factorization in an active learning setting. Such a system is shown to be feasible and can be carried out using significantly fewer rated items than previously proposed static inference methods.

System And Method For Recommending Items In A Social Network

View page
US Patent:
20150199715, Jul 16, 2015
Filed:
Jun 27, 2013
Appl. No.:
14/411856
Inventors:
- Issy de Moulineaux, FR
Branislav Kveton - San Jose CA, US
Marc LeLarge - Paris, FR
Smriti Bhagat - San Francisco CA, US
International Classification:
G06Q 30/02
G06Q 50/00
Abstract:
The present principles consider stochastic bandits with side observations, a model that accounts for both the exploration/exploitation dilemma and relationships between arms. In this setting, after pulling an arm i, the decision maker also observes the rewards for some other actions related to i. The present principles provide a method and a system for efficiently leveraging additional information based on the responses provided by other users connected to the user via a computerized social network and derive new bounds improving on standard regret guarantees. We will see that this model is suited to content recommendation in social networks, where users' reactions may be endorsed or not by their friends.

Scientific Casting Method And Apparatus

View page
US Patent:
20150161628, Jun 11, 2015
Filed:
Dec 6, 2013
Appl. No.:
14/098595
Inventors:
- Issy de Moulineaux, FR
Smriti Bhagat - San Francisco CA, US
International Classification:
G06Q 30/02
Abstract:
A method for recommending at least one element of an audio-visual program commences by first determining the success of an audio-visual program composed of a set elements initially selected by a user. Thereafter, a replacement element is substituted for at least one of the initially selected elements and the success of the audio-visual program with the replacement element is determined. Thereafter, the replacement element is recommended for substitution in place of the at least one initially selected element if substituting replacement element in the audio-visual program yields greater success.

Method And Apparatus For Inferring User Demographics

View page
US Patent:
20150112812, Apr 23, 2015
Filed:
Jun 10, 2013
Appl. No.:
14/407114
Inventors:
- Issy de Moulineaux, FR
Smriti Bhagat - San Francisco CA, US
Stratis Ioannidis - San Francisco CA, US
Nina Taft - San Francisco CA, US
International Classification:
G06Q 30/02
US Classification:
705 1466
Abstract:
A method to determine demographic information of a new user utilizing only ratings includes training an inference engine informed with a training data set which includes ratings and demographic information from a plurality of other users. The new user inputs ratings, such as movie ratings, and an inference engine determines demographic information of the new user. The demographic information of the new user can then be used to provide recommendations or to provide targeted advertisements to the new user.
Control profile
Smriti Bhagat from New York, NY, age ~44 Get Report