Rohit Babbar


Hello, I work in the Empirical Inference group headed by Prof. Bernhard Schölkopf , at Max-Planck Institute for Intelligent Systems, Tübingen, Germany. 

Research interests : Machine Learning for large-scale problems, Extreme Classification, Deep Learning, and Optimization... 

Before this, I finished my PhD in October 2014 from LIG lab of University of Grenoble Alpes,  France, where I was advised by Prof. Eric Gaussier and Prof. Massih-Reza Amini under the Class-Y project funded by the French National Research Agency (ANR). 


Extreme Classification Repository  - Maintained by Manik Varma, consists of Datasets and (links to) code for most recent methods for extreme classification





We are organizing MPI-ETH Pre-doc Summer School on Learning Systems from July 3 to Friday July 7, 2017 in Zürich, Switzerland for Master's students. Please encourage your students to apply.



Publications:

    2017
  • DiSMEC : Distributed Sparse Machines for Extreme Multi-label Classificationpdf Code
    Rohit Babbar and  Bernhard Schölkopf
    ACM International Conference on Web Search and Data Mining (
    WSDM) 2017, Cambridge;
    Also accepted for NIPS 2016 Extreme Classification Workshop
   2016
  • TerseSVM : A scalable approach for learning compact models in Large-scale classification, pdf
    Rohit Babbar, Krikamol Muandet, and  Bernhard Schölkopf
    SIAM International Conference on Data Mining (
    SDM 2016), Miami, (pls email me for the code)

  • Learning Taxonomy Adaptation in Large-scale Classification
    Rohit Babbar, Ioannis Partalas, Eric Gaussier and Massih-reza Amini
    Journal of Machine Learning Research , (JMLR 2016)
   2015
  • Efficient Model Selection for Regularized Classification by Exploiting Unlabeled Data 
    Georgios Balikas, Ioannis Partalas, Eric Gaussier, Rohit Babbar and Massih-Reza Amini
    International Symposium on Intelligent Data Analysis, (IDA 2015),  Saint-Etienne, France
   2014
  • Re-ranking Approach to Classification in Large-scale Power-law Distributed Category Systems, pdf
    Rohit Babbar, Ioannis Partalas, Eric Gaussier and Massih-reza Amini
    ACM SIGIR Conference , (
    SIGIR 2014), Gold Coast, Australia, 
  • On Power Law Distributions in Large-scale Taxonomies", pdf
    Rohit BabbarCornelia Metzig,  Ioannis Partalas, Eric Gaussier and Massih-reza Amini
    SIGKDD Explorations Journal, Special Issue on Big Data
  2013
  • On Flat versus Hierarchical Classification in Large-Scale Taxonomies", pdf  
    Rohit Babbar, Ioannis Partalas, Eric Gaussier and Massih-reza Amini
    Neural Information Processing Systems, (
    NIPS 2013), Lake Tahoe, Neveda, USA

  • Maximum-margin Framework for Training Data Synchronization in Large-scale Hierarchical Classification, pdf, 
    Rohit Babbar, Ioannis Partalas, Eric Gaussier and Massih-reza Amini 
    Intl. Conference on Neural Information Processing, (
    ICONIP 2013), Daegu, Korea

  • Comparative Classifier Evaluation for Web-scale Taxonomies using Power Law, 
    Rohit Babbar, Ioannis Partalas, Cornelia Metzig, Eric Gaussier and Massih-reza Amini
    European Semantic Web Conference (
    ESWC 2013), Montpiller, France.
   2012
  • On Empirical Tradeoffs in Large Scale Hierarchical Classification
    Rohit Babbar, Ioannis Partalas, Eric Gaussier, Cecile Amblard
    ACM Intl. Conference on Information and Knowledge Management, (
    CIKM 2012), Maui, Hawaii.

  • Adaptive Classifier Selection in Large-scale Hierarchical Classification
    Ioannis Partalas, Rohit Babbar, Eric Gaussier, Cecile Amblard
    Intl. Conference on Neural Information Processing, (
    ICONIP 2012), Doha, Qatar.


Educational Background :
  • Doctoral Degree in Computer Science from University of Grenoble Alpes, defended in October 2014.
  • Master in Computer Science, 2009-2011, from Chennai Mathematical Institute, India. Did my master thesis(Jan-June, 2011) under supervision of Dr. Manik Varma and Prof. Madhavan Mukund to study the regularization path for p-norm Multiple Kernel Learning

  • B. Tech. from NIT Kurukshetra, in ECE (2000-2004), worked in IBM India from 2004 to 2009.

Talks :
  • ABC Team, LORIA, Nancy, November, 2016
  • Big Data for Material Sciences Workhsop, Ringberg Castle, July 2016
  • Data Analytics Lab, ETH Zurich, November 2015
  • Bosch Corporate Research Center, Renningen, October 2015
  • Magnet Team, INRIA, Lille, December 2014

Other Talks/Poster Presentations :
  • WSDM 2017, Cambridge
  • NIPS XMC workshop 2016, Barcelona
  • SDM 2016, Miami
  • SIGIR 2014, Gold Coast
  • NIPS 2013, Lake Tahoe
  • ICONIP 2013, Daegu
  • CIKM 2012, Hawaii

Other Stuff

- Long ago, finished Grenoble-Vizille Semi-marathon


Locations of Site Visitors
Ċ
dismec.pdf
(406k)
Rohit Babbar,
Sep 8, 2016, 12:31 PM
Ċ
Rohit Babbar,
Jul 9, 2014, 3:13 PM
Ċ
siam.pdf
(256k)
Rohit Babbar,
Sep 8, 2016, 12:10 PM
Ċ
Rohit Babbar,
Jul 9, 2014, 3:05 PM
Comments