My Research :


Research Interests : Machine Learning, Statistical Learning Theory, Online Learning, Optimization, Empirical Process Theory, Concentration Inequalities, Game Theory


Publications :

A. Preprints


1. Empirical Entropy, Minimax Regret and Minimax Risk
   Alexander Rakhlin, Karthik Sridharan, Alexandre Tsybakov
   [pdf]

2. On Convex Optimization, Fat Shattering and Learning
   Nathan Srebro, Karthik Sridharan
   [pdf]
   
   B. Conferences

3. Online Nonparametric Regression
   Alexander Rakhlin, Karthik Sridharan
   COLT 2014 [pdf]

4. On Martingale Extensions of Vapnik-Chervonenkis Theory with Applications to Online Learning
   Alexander Rakhlin, Karthik Sridharan
   To appear in Book Chapter : Festschrift in honor of A. Chervonenkis. [pdf]

5. On Semi-Probabilistic Universal Prediction
   Alexander Rakhlin, Karthik Sridharan
   Proceedings of IEEE Information Theory Workshop, 2013. Invited paper [pdf]

6. Optimization, Learning, and Games with Predictable Sequences
   Alexander Rakhlin, Karthik Sridharan
   NIPS 2013 [pdf]

7. Competing With Strategies
   Wei Han, Alexander Rakhlin, Karthik Sridharan
   COLT 2013 [pdf]

8. Online Learning with Predictable Sequences
   Alexander Rakhlin, Karthik Sridharan
   COLT 2013 [pdf] , [Arxiv version]

9. Localization and Adaptation in Online Learning (full oral presentation)
   Alexander Rakhlin, Ohad Shamir, Karthik Sridharan
   AISTATS 2013

10. Relax and Randomize: From Value to Algorithms (full oral presentation)
    Alexander Rakhlin, Ohad Shamir, Karthik Sridharan
    NIPS 2012 [pdf]

11. Making Stochastic Gradient Descent Optimal for Strongly Convex Problems
    Alexander Rakhlin, Ohad Shamir, Karthik Sridharan
    ICML 2012 [Arxiv Version]

12. Minimizing The Misclassification Error Rate Using a Surrogate Convex Loss
    Shai Ben-David, David Loker, Nathan Srebro, Karthik Sridharan
    ICML 2012 [pdf]

13. On the Universality of Online Mirror Descent
    Nathan Srebro, Karthik Sridharan, Ambuj Tewari
    NIPS 2011 [Arxiv Version]

14. Better Mini-Batch Algorithms via Accelerated Gradient Methods
    Andrew Cotter, Ohad Shamir , Nathan Srebro, Karthik Sridharan
    NIPS 2011 [Arxiv Version]

15. Online Learning: Stochastic and Constrained Adversaries
    Alexander Rakhlin, Karthik Sridharan, Ambuj Tewari
    NIPS 2011 [pdf]   [Arxiv Version]

16. Online Learning: Beyond Regret (best paper award)
    Alexander Rakhlin, Karthik Sridharan, Ambuj Tewari
    COLT 2011, [pdf]   [Arxiv Version]

17. Complexity-Based Approach to Calibration with Checking Rules
    Dean Foster, Alexander Rakhlin, Karthik Sridharan, Ambuj Tewari
    COLT 2011, [pdf]  

18. Online Learning: Random Averages, Combinatorial Parameters and Learnability (full oral presentation)
    Alexander Rakhlin, Karthik Sridharan, Ambuj Tewari
    NIPS 2010 [pdf]   [Arxiv Version]

19. Smoothness, Low-Noise and Fast Rates
    Nathan Srebro, Karthik Sridharan, Ambuj Tewari
    NIPS 2010 [pdf]   [Arxiv version]

20. Robust Selective Sampling from Single and Multiple Teachers
    Ofer Dekel, Claudio Gentile, Karthik Sridharan
    COLT 2010 [pdf]

21. Convex Games in Banach Spaces
    Karthik Sridharan, Ambuj Tewari
    COLT 2010 [pdf]

22. Learning Kernel-Based Halfspaces with the Zero-One Loss (best paper award)
    Shai Shalev-Shwartz, Ohad Shamir, Karthik Sridharan
    COLT 2010 [pdf], A shorter version presented at the best paper track IJCAI 2011 [pdf]

23. Learning exponential families in high-dimensions: Strong convexity and sparsity
    Sham Kakade, Ohad Shamir, Karthik Sridharan, Ambuj Tewari
    AISTATS 2010 [Arxiv version]

24. The Complexity of Improperly Learning Large Margin Halfspaces
    Shai Shalev-Shwartz, Ohad Shamir, Karthik Sridharan
    Open Problems, COLT 2009 [pdf]

25. Learnability and Stability in the General Learning Setting
    Shai Shalev-Shwartz, Ohad Shamir, Nathan Srebro, Karthik Sridharan
    COLT 2009 [pdf]

26. Stochastic Convex Optimization
    Shai Shalev-Shwartz, Ohad Shamir, Nathan Srebro, Karthik Sridharan
    COLT 2009 [pdf]

27. Multi-View Clustering via Canonical Correlation Analysis
    Kamalika Chaudhuri, Sham Kakade, Karen Livescu, Karthik Sridharan
    ICML 2009 [pdf]

28. On the Complexity of Linear Prediction: Risk Bounds, Margin Bounds and Regularization
    Sham Kakade, Karthik Sridharan, Ambuj Tewari
    NIPS 2008 [pdf]

29. Fast Rates for Regularized Objectives
    Shai Shalev-Shwartz, Nathan Srebro, Karthik Sridharan
    NIPS 2008 [pdf]

30. Information Theoretic Framework for Multi-view Learning
    Karthik Sridharan, Sham M. Kakade
    21st Annual Conference on Learning Theory (COLT 2008) [pdf]

31. Competitive Mixtures of Simple Neurons
    Karthik Sridharan, Matthew J Beal, Venu Govindaraju
    ICPR'06 [pdf]

32. Identifying handwritten text in mixed documents
    Faisal Farooq, Karthik Sridharan, Venu Govindaraju
    ICPR'06

33. Classification of Machine Print and Handwritten Arabic Documents
    Karthik Sridharan, Faisal Farooq, Venu Govindaraju
    (SDIUT 2005, pp. 89-94.)

34. A Sampling Based Approach to Facial Feature Extraction IEEE link
    Karthik Sridharan, Venu Govindaraju
    (IEEE AUTOID 2005. Best Paper Award - Second Prize, pp.51-56)

35. A Probabilistic Approach to Semantic Face Retrieval springer link
    Karthik Sridharan, Sankalp Nayak, Sharat Chikkerur, Venu Govindaraju
    (AVBPA 2005, pp.977-986.)

36. A Dynamic Migration Model for Self-adaptive Genetic Algorithms springer link
    K.G. Srinivasa, Karthik Sridharan, P. Deepa Shenoy, Venugopal K.R., L.M. Patnaik
    (Proceedings of 6th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL 05),
    Springer Verlag, LNCS, July 6th – 9th 2005, Brisbane, Australia, pp. 555-562.)

37. An Effective Content-Based Image Retrieval System Using STI Features and Relevance Feedback
    K.G. Srinivasa, Karthik Sridharan, P. Deepa Shenoy, Venugopal K.R., L.M. Patnaik
    (KBCS-2004, Fifth International Conference On Knowledge Based Computer Systems,
    Hyderabad, India, December 19-22, 2004, pp. 290 - 301.)

38. EASOM: An Efficient Soft Computing Method for Predicting the Share Values ACTA press link
    K.G. Srinivasa, Karthik Sridharan, P. Deepa Shenoy, Venugopal K.R., L.M. Patnaik
    (Proceedings of IASTED International Conference on Artificial Intelligence and Applications (AIA 2004), ISSN: 1027-2666,
    Austria, Innsburg, Feb 16 - 18, 2004, pp. 264-269.)
    
    
    C. Journals

39. Sequential Complexities and Uniform Martingale Laws of Large Numbers
    Alexander Rakhlin, Karthik Sridharan, Ambuj Tewari
    Probability Theory and Related Fields, 2014, to appear [pdf]

40. Selective Sampling and Active Learning from Single and Multiple Teachers
    Ofer Dekel, Claudio Gentile, Karthik Sridharan
    Journal of Machine Learning Research, 2012 [pdf]

41. Learning Kernel Based Halfspaces with the 0-1 Loss
    Shai Shalev-Shwartz, Ohad Shamir, Karthik Sridharan
    SIAM Journal on Computing, 40(6):1623-1646, 2011 [pdf]

42. Learnability, Stability and Uniform Convergence
    Shai Shalev-Shwartz, Ohad Shamir, Nathan Srebro, Karthik Sridharan
    Journal of Machine Learning Research, 11(Oct):2635-2670, 2010 [pdf]

43. A Neural Network based CBIR System using STI Features and Relevance Feedback
    K.G. Srinivasa, Karthik Sridharan, P. Deepa Shenoy, Venugopal K.R., L.M. Patnaik
    International Journal on Intelligent Data Analysis, Volume 10, Number 2, 2006, IOS Press.
    
    
    D. Thesis  

44. Doctoral Thesis : Learning from an Optimization Viewpoint
    Karthik Sridharan Advisor : Nati Srebro
    Thesis Commitee : David McAllester, Arkadi Nemirovski, Alexander Razborov, Nathan Srebro
    Toyota Technological Institute at Chicago
    [pdf]
     

45. Master's Thesis : Semantic Face Retrieval
    Karthik Sridharan
    Advisor : Venu Govindaraju
    Computer Science, SUNY Buffalo, 2006
    [pdf]
    
    
    E. Lecture Notes

46. Statistical Learning Theory and Sequential Prediction
    Alexander Rakhlin, Karthik Sridharan
    STAT 298, Lecture Notes [pdf]
    
    F. Notes  

47. A Gentle Introduction to Concentration Inequalities
    Karthik Sridharan
    (Theorems and proofs of a few concentration inequalities) - [pdf] [ps] [dvi] [gzipped]

48. Fast Convergence Rates for Excess Regularized Risk with Application to SVM
    Karthik Sridharan
    [pdf]

49. Note on Refined Dudley Integral Covering Number Bound
    Nathan Srebro, Karthik Sridharan
    [pdf]
    
    
    G. National Conferences in India  

50. A Novel Neural Network Approach for Face Detection and Recognition
    Karthik Sridharan
    (Award winning paper at Young IT Professional Award 2003, south regional of Computer Society of India, Bangalore chapter.)

51. A Counterpropagation Neural Network for Face Detection and Recognition
    Karthik Sridharan , Jibi Abraham
    (SPIN 2003 national conference, Bangalore.)

1. Semantic Face Retrieval System
   The descriptions that people provide about human faces are often verbal in nature like, "blonde haired person" or "person with long face". The project involves automatically extracting such semantic descriptions of faces from the image database and performing query about a particular face using verbal descriptions more efficient. We currently are using Pruning of images based on description leads to loss of the right images due to mistakes by the automated retrieval system or the user. Hence we use Bayesian Learning for the query and retrieval part.

2. EM Based Probabilistic Neural Network for Supervised Learning

3. AROMA - A Recursive Optimization method using Multi-resolution Analysis

4. Musical Instrument Recognition using Gaussian Mixture Model
   Based on features like the spectogram, psd, the LP co-efficients of a music wave file, a mixture of gaussians can be used to model the extracted features and hence recognize the instrument playing the piece of music. The project was carried out in MATLAB and was my final year undergraduate project.

5. Face Detection and Recognition using Neural Network
   A Conuterpropagation neural network was used for face detection and recognition in 2d images. The neural network was modeled such that by just changing the supervised portion of the counter propagation network, face recognition could be done with the same network trained to do face detection. This was my 3rd year (6th sem) undergraduate project.

1. Matlab code for Metropolis Hasting Sampling (define in func.m the density function)
   Metropolis, N., and S. Ulam. 1949. The Monte Carlo method. J. Amer. Statist. Assoc. 44: 335–341

2. Matlab code for slice sampling (define in func.m the density function)
   Neal, R. M. (2003) ``Slice sampling'' (with discussion), Annals of Statistics, vol. 31, pp. 705-767