P Balamurugan

Assistant Professor

Industrial Engineering and Operations Research (IEOR)

Indian Institute of Technology, Bombay (IIT-B)

Powai, Mumbai, Maharashtra, India.

email: balamurugan.palaniappan@iitb.ac.in

Research Interests

My primary research theme is to develop efficient optimization methods and algorithms for various machine learning, data mining problems. This involves investigation of both the theoretical and practical aspects of optimization methodologies. The interplay between statistical, learning theoretic, algorithmic and probabilistic aspects of machine learning models also fascinate me. I am also interested in looking into applications of machine learning and data mining in relatively less explored directions.

Courses (Ongoing)

    • IE 643: Deep Learning - Theory and Practice (Links will be put up soon)
    • IE 507: Modeling & Computation Lab along with Prof. Veeraruna Kavitha.

Courses (Past)

    • IE 712: Selected Applications of Stochastic Models course along with Prof. N. Hemachandra.
    • IE 613: Online Machine Learning course along with Prof. Manjesh Hanawal.
    • IE 684: IEOR Lab along with Prof. Ashutosh Mahajan.



    • Modeling Label Interactions in Multi-label Classification: A Multi-structure SVM Perspective.



    • Stochastic Variance Reduction Methods for Saddle-Point Problems.
      • P. Balamurugan, Francis Bach.
      • In Advances in Neural Information Processing Systems (NIPS), 2016. [pdf] [code]

    • Gaussian Process Pseudo-Likelihood Models for Sequence Labeling.
      • P. K. Srijith, P. Balamurugan, Shirish Shevade.
      • In European Conference on Machine Learning and Principles and Practice of Knowledge Discovery (ECML-PKDD), 2016. [pdf]

    • ADMM for Training Sparse Structural SVMs with augmented L1 regularizers.



    • Scalable sequential alternating proximal methods for sparse structural SVMs and CRFs.
      • P. Balamurugan, Shirish Shevade, T. Ravindra Babu.
      • In Knowledge and Information Systems. Vol. 38(3), pages: 599-621., 2014. [pdf]


    • Large-Scale Elastic Net Regularized Linear Classification SVMs and Logistic Regression.
      • P. Balamurugan.
      • In IEEE International Conference on Data Mining (ICDM), 2013. Acceptance Rate: 19.65% (159/809) [pdf]

    • Optimizing F-Measure With Non-Convex Loss and Sparse Linear Classifiers.


    • Sequential Alternating Proximal Method for Scalable Sparse Structural SVMs.
      • P. Balamurugan, Shirish Shevade, T. Ravindra Babu. (One of the Best Papers invited for KAIS journal).
      • (Full Paper) In IEEE International Conference on Data Mining (ICDM), 2012. Acceptance Rate for full papers: 10.71% (81/756). [pdf]
      • Code for a fast version of sequential alternating proximal method along with other training methods available at [code link]

    • Efficient Algorithms for Linear Summed Error Structural SVMs.
      • P. Balamurugan, Shirish Shevade, T. Ravindra Babu.
      • In International Joint Conference on Neural Networks (IJCNN), 2012. [pdf]


Workshop Papers

    • Robust Discriminative Clustering with Sparse Regularizers.

    • Efficient Variational Inference for Gaussian Process Structured Prediction.

Technical Reports and Preprints

    • Stochastic Variance Reduction Methods for Saddle-Point Problems.


I delivered lectures on Basics of Convex Optimization and Proximal Methods in a TEQIP sponsored workshop on Role of Optimization in Engineering Applications organized by the Department of Electronics and Communication Engineering, VNIT Nagpur, during December 28-29, 2017.

Post-doctoral Research

During January 2015-December 2016, I was a post doctoral researcher at SIERRA Project Team, INRIA-Ecole Normale Superieure mentored by Professor Francis Bach.

During January-September 2017, I was a post-doc in the Signal, Statistique et Apprentissage (S2A) Group, Telecom-ParisTech, Paris, where I was mentored by Professor Stéphan Clémençon and Professor Florence d’Alché-Buc.

Education Details

  • I was a PhD student at Intelligent Systems Lab, headed by Prof. Shirish K. Shevade, in the department of Computer Science and Automation, Indian Institute of Science, Bangalore, India.
    • My PhD thesis focused on developing fast optimization methods for structured prediction and sparse classification problems.
    • Thesis Review Committee: Professor Inderjit S. Dhillon, University of Texas, Austin, USA and Professor Ashish Ghosh, Indian Statistical Institute, Kolkata, India.

Work Experience

    • Research Intern at IBM India Research Lab, Bangalore, during May-August, 2013. Mentor: Dr. Vikas C. Raykar.
    • Project Assistant under Dr. Shirish Shevade during August 2009 - December 2009. Worked on "Efficient Algorithms for Structured Prediction".
    • Assistant Systems Engineer at Tata Consultancy Services during 2004 - 2007.

Teaching Assistance

    • Teaching Assistant for Big Data course. (February-May 2017)
    • Teaching Assistant for Introduction to Machine Learning course by Prof. Florence d’Alché-Buc. (February-May 2017)
    • Teaching Assistant for Probability and Statistics course by Dr. Indrajit Bhattacharya. (August-December 2011)

M.E. Thesis

    • L1-Norm Structural Classification SVMs.


    • Recipient of the Alumni Medal from Computer Science and Automation Department, Indian Institute of Science, for the Best PhD Thesis in 2015.
    • A co-recipient of IBM Best PhD Thesis Award among theses from Computer Science and Automation Department, Indian Institute of Science, for the year 2015.
    • IBM PhD Fellowship awards for the years 2012 and 2013.
    • Travel awards from IBM, Infosys India, Indian Institute of Science (Sarukkai Jagannathan award) and IEEE ICDM.

Review Responsibility

    • A reviewer for Indian Workshop on Machine Learning (iWML) 2018, Mathematics of Operations Research Journal, US-Israel BSF Research Proposal, NIPS 2016, Neuro Computing Journal, Neural Networks Journal, Science China Mathematics Journal, and Sadhana Academy Proceedings in Engineering Sciences.

Other Activities