Shubhendu Trivedi

Shubhendu Trivedi

(I avoid mugshots!)

About Me and Research Interests

I am a PhD candidate with broad interests in Machine Learning with an emphasis to applications in Computer Vision. In particular, I have a predilection for (deep and otherwise) representation learning, structured prediction and general semi/weakly supervised learning. Currently however, I have been exploring problems in Discriminative (Linear/Non-linear) Metric/Similarity Learning and Semantic Hashing (i.e. Learning to Hash). I also dabble in Combinatorics and have a weakness for all things Spectral; where my interests remain very strong.

For my research I consider myself very fortunate to be working under the supervision of Prof. Gregory Shakhnarovich. Prior to this I completed a MS (focusing on Machine Learning) while on the way to candidacy. Before that, in what now seems like a past life, I worked on problems in Educational Analytics, Clustering and Ensemble Learning under the supervision of Professors Neil T. Heffernan and Gábor N. Sárközy earning another MS (in Computer Science, here's the proof! ) with a thesis (Prof. Sonia Chernova was the reader) that presented a new clustering algorithm based on the Szemerédi Regularity Lemma and also a method somewhat similar to mixture of experts using clustering for ensemble learning. My work that led to the MS thesis was awarded the best in the university in the Science category both in 2011 and 2012, in an annual competition in which MS and PhD students presented their work as posters. Further afield, I worked in the industry in the signal processing domain (Application Specific Integrated Circuits) for roughly one year after acquiring an undergraduate degree in Electronics and Communications Engineering. While working I also helped my undergraduate advisor, Dr. (Mrs) K. R. Joshi, in teaching three senior year courses. During my undergrad, I worked on biometrics (face and speech recognition - using subspace projection methods for the former and dynamic programming for the latter. This work, that also involved implementing a low cost (~$1) speech recognizer on a microcontroller, was awarded the best undergraduate project in the institute that year). At the same time I also worked on blind source separation with applications to Magnetic Resonance image denoising.

I can be reached on email at shubhendu@{cs.uchicago or ttic}.edu

Recent/Refereed Research Reports

  • Discriminative Metric Learning by Neighborhood Gerrymandering
    Shubhendu Trivedi, David McAllester, Greg Shakhnarovich.
    Proc. Neural Information Processing Systems 2014, Montreal, Canada.

  • A Consistent Estimator of the Expected Gradient Outerproduct
    Shubhendu Trivedi, Jialei Wang, Samory Kpotufe, Greg Shakhnarovich.
    Proc. Uncertainity in Artificial Intelligence 2014, Quebec City, Canada.

  • Applying Clustering to the Problem of Predicting Retention within an ITS: Comparing Regularity Clustering with Traditional Methods.
    Fei Song, Shubhendu Trivedi, Yu Tao Wang, Gábor N. Sárközy, Neil T. Heffernan.
    AAAI FLAIRS 2013, St. Pete Beach, FL, United States. (older version)

  • A Practical Regularity Partitioning Algorithm and its Applications in Clustering
    Gábor N. Sárközy, Fei Song, Endre Szemerédi, Shubhendu Trivedi.
    arXiv preprint arXiv:1209.6540, 2012

  • The real world significance of performance prediction
    Zachary A. Pardos, Qing Yang Wang, Shubhendu Trivedi.
    Proc. Educational Data Mining 2012, Chania, Greece

  • Co-Clustering by Bipartite Spectral Graph Partitioning for Out-of-Tutor Prediction
    Shubhendu Trivedi, Zachary A. Pardos, Gábor N. Sárközy, Neil T. Heffernan
    Proc. Educational Data Mining 2012, Chania, Greece

  • Clustered Knowledge Tracing
    Zachary A. Pardos, Shubhendu Trivedi, Neil T. Heffernan, Gábor N. Sárközy
    Proc. Intelligent Tutoring Systems 2012, Chania, Greece

  • Spectral Clustering in Educational Data Mining
    Shubhendu Trivedi, Zachary A. Pardos, Gábor N. Sárközy, Neil T. Heffernan
    Proc. Educational Data Mining 2011, Eindhoven, Netherlands

  • Clustering students to generate an ensemble to improve standard test score predictions
    Shubhendu Trivedi, Zachary A. Pardos, Neil T. Heffernan
    Proc. Artificial Intelligence in Education 2011, Auckland, New Zealand

  • Notes/Unpublished Works/Theses/Working Documents

  • The Jacobian Outerproduct and a Consistent Estimator
    Shubhendu Trivedi.
    (PDF coming soon, extends the work in the UAI 2014 paper to the multiclass case)

  • Notes on Asymmetric Metric Learning for kNN Classification
    Shubhendu Trivedi.
    Notes, November 2015
    Working document, PDF

  • The Utility of Clustering in Prediction Tasks
    Shubhendu Trivedi, Zachary A. Pardos, Neil T. Heffernan.
    Unpublished Technical Report, 05 September 2011
    arXiv version: arXiv 1509.06163
    (An early, mostly experimental project report that investigates how to leverage clustering to improve prediction)

  • Slides for "Deep Learning" (Upcoming MIT Press book by Goodfellow, Bengio and Courville)

  • Beyond Mahalanobis: A Survey on Non-Linear Metric Learning
    Shubhendu Trivedi.
    Working document, PDF coming soon

  • A Graph-Theoretic Clustering Algorithm based on the Regularity Lemma and Strategies to Exploit Clustering for Prediction
    Shubhendu Trivedi.
    MS Thesis, 2012

  • Teaching

    As Teaching Assistant:

    Undergraduate Courses:
    -- CS 4120 Analysis of Algorithms (Instructor: Dr. Gábor N. Sárközy, Textbook: CLRS/Kleinberg-Tardos)
    -- CS 2223 Introduction to Algorithms wih Lua (Instructor: Dr. Joshua D. Guttman, Textbook: CLRS)
    -- CS 3133 Foundations of Computer Science i.e Automata Theory (Instructor: Dr. Gábor N. Sárközy, Textbook: Sudkamp)
    -- CS 4341 Introduction to Artificial Intelligence (Instructor: Dr. Neil T. Heffernan, Textbook: Russell and Norvig)
    -- MA 2201 Discrete Mathematics (Instructor: Dr. Gábor N. Sárközy, Textbook: Kenneth Rosen)
    -- CS 2223 Introduction to Algorithms wih Lua (Instructor: Dr. Joshua D. Guttman, Textbook: CLRS)
    -- CS 3133 Foundations of Computer Science i.e Automata Theory (Instructor: Dr. Gábor N. Sárközy, Textbook: Sudkamp, Dexter Kozen)
    -- CS 2011 Introduction to Machine Organization and Assembly Language (Instructor: Dr. Hugh C. Lauer, Textbook: Bryant and Halloran)

    -- STAT 27725/CMSC 25400 Machine Learning (Instructor: Dr. Imre Risi Kondor) (Best teaching assistant award)
    (Slides from some lectures I gave in this course:
    Discrete Probability Tutorial | Maximum Likelihood Estimation and Multivariate Gaussians
    Artificial Neural Networks I | Artificial Neural Networks II)

    Graduate Courses:
    -- CS 534 Artificial Intelligence (Instructor: Dr. Neil T. Heffernan, Textbook: Russell and Norvig)
    -- TTIC 31020 Introduction to Statistical Machine Learning (Instructor: Dr. Gregory Shakhnarovich)

    As Co-Instructor:

    Undergraduate Courses:
    -- Introduction to Digital Image Processing (Textbook: Gonzalez and Woods)
    -- Image and Signal Processing Lab
    -- Introduction to Bioinformatics (mostly covered the part on data mining)

    Graduate Courses:
    -- Deep Learning (CMSC 35246, Textbook: Bengio, Goodfellow, Courville)


    Coming soon


    My Erdos Number is 2*. My Bacon Number is ∞. I don't eat Bacon.
    *( Paths: ST <--> Gábor N. Sárközy <--> Paul Erdos and ST <--> Endre Szemerédi <--> Paul Erdos)

    Elsewhere on the Internet:

    -- Google Scholar (Scholar apparently picks up informal articles/blog posts that get cited and these are included here)
    -- Onionesque Reality (a blog, mostly on random things)
    -- Goodreads (again, not too frequently updated, it is hard to catch up with my own reading speed ;)
    -- Twitter (use twitter mostly as an advanced RSS feed to follow more recent work in Machine Learning)