Publications

Journal / preprints

  • Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networks
    Behnam Neyshabur, Zhiyuan Li, Srinadh Bhojanapalli, Yann LeCun, Nathan Srebro
    preprint , [Arxiv].

  • Stabilizing GAN Training with Multiple Random Projections
    Behnam Neyshabur, Srinadh Bhojanapalli, Ayan Chakrabarti
    preprint , [Arxiv], [Project website].

  • Provable Burer-Monteiro factorization for a class of norm-constrained matrix problems
    Dohyung Park, Anastasios Kyrillidis, Srinadh Bhojanapalli, Constantine Caramanis, Sujay Sanghavi
    preprint , [Arxiv].

  • A New Sampling Technique for Tensors
    Srinadh Bhojanapalli, Sujay Sanghavi
    preprint, [Arxiv], [slides].

  • Completing any Low-rank Matrix, Provably
    Yudong Chen, Srinadh Bhojanapalli, Sujay Sanghavi, Rachel Ward
    Journal of Machine Learning Research (JMLR) 2015
    [Arxiv], [JMLR].

Conference

  • Smoothed analysis for low-rank solutions to semidefinite programs in quadratic penalty form
    Srinadh Bhojanapalli, Nicolas Boumal, Prateek Jain, Praneeth Netrapalli
    Conference on Learning Theory (COLT) 2018
    [Arxiv].

  • A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks
    Behnam Neyshabur, Srinadh Bhojanapalli, Nathan Srebro
    International Conference on Learning Representations (ICLR) 2018
    [Arxiv].

  • Exploring Generalization in Deep Learning
    Behnam Neyshabur, Srinadh Bhojanapalli, David McAllester, Nathan Srebro
    Neural Information Processing Systems (NIPS) 2017
    [Arxiv].

  • Implicit Regularization in Matrix Factorization
    Suriya Gunasekar, Blake Woodworth, Srinadh Bhojanapalli, Behnam Neyshabur, Nathan Srebro
    Neural Information Processing Systems (NIPS) 2017
    [Arxiv], [slides].

  • Single Pass PCA of Matrix Products
    Shanshan Wu, Srinadh Bhojanapalli, Sujay Sanghavi, Alex Dimakis
    Neural Information Processing Systems (NIPS) 2016
    [Arxiv], [SPARK code].

  • Global Optimality of Local Search for Low Rank Matrix Recovery
    Srinadh Bhojanapalli, Behnam Neyshabur, Nathan Srebro
    Neural Information Processing Systems (NIPS) 2016
    [Arxiv].

  • Dropping Convexity for Faster Semi-definite Optimization
    Srinadh Bhojanapalli, Anastasios Kyrillidis, Sujay Sanghavi
    Conference on Learning Theory (COLT) 2016
    [Arxiv], [COLT], [slides].

  • Tighter Low-rank Approximation via Sampling the Leveraged Element
    Srinadh Bhojanapalli, Prateek Jain, Sujay Sanghavi
    ACM-SIAM Symposium On Discrete Algorithms (SODA) 2015
    [Arxiv], [SODA], [slides].

  • Universal Matrix Completion
    Srinadh Bhojanapalli, Prateek Jain
    International Conference on Machine Learning (ICML) 2014
    [Arxiv], [ICML], [slides], [video].

  • Coherent Matrix Completion
    Yudong Chen, Srinadh Bhojanapalli, Sujay Sanghavi, Rachel Ward
    International Conference on Machine Learning (ICML) 2014
    [Arxiv], [ICML], [slides], [video].

PhD Thesis

Large Scale Matrix Factorization with Guarantees: Sampling and Bi-linearity [pdf]
UT Austin, 2015.