Vivek Bharadwaj

I am an EECS graduate student at UC Berkeley, advised by the fantastic pair Jim Demmel and Aydın Buluç. I'm associated with the BeBOP and PASSION groups, and I'm supported by a Department of Energy Computational Science Graduate Fellowship from the Krell Institute.

    Interests
  • Geometric Deep Learning
  • Sparse Computations
  • Randomized Sketches
  • Graph Algorithms
    Background
  • PhD in Computer Science.
    UC Berkeley, 2020-Present
  • BS in CS + Mathematics.
    Caltech, 2016-2020

Email: firstname_lastname [at] berkeley.edu

images/prof_pic.jpg
images/prof_pic.jpg

I am an EECS graduate student at UC Berkeley, advised by the fantastic pair Jim Demmel and Aydın Buluç. I'm associated with the BeBOP and PASSION groups, and I'm supported by a Department of Energy Computational Science Graduate Fellowship from the Krell Institute.

    Interests
  • Geometric Deep Learning
  • Sparse Computations
  • Randomized Sketches
  • Graph Algorithms
    Background
  • PhD in Computer Science.
    UC Berkeley, 2020-Present
  • BS in CS + Mathematics.
    Caltech, 2016-2020

Email: firstname_lastname [at] berkeley.edu


news

Jul 12, 2025   
07/12/25  
On July 21 at 10AM PDT, I will give my 🎉 🎉 dissertation exit talk 🎉 🎉! You are welcome to attend, either virtually or in-person on UC Berkeley's campus. Find the details here.
Jun 22, 2025   
06/22/25  
I'm presenting this poster at LBNL's Deep Learning for Science workshop - stop by to chat if you're attending.
Apr 5, 2025   
04/05/25  
OpenEquivariance was accepted to SIAM ACDA 2025! See you in Montréal.

recent & upcoming talks

  1.  

    Jul 15, 2025
    DOE CSGF Program Review, Washington, D.C.
    Final Year Fellow Presentation (Chemistry Graph Neural Networks)

     

    Mar 4, 2025
    Engineering Fast Kernels for Rotation-Equivariant Deep Neural Networks

     

    Nov 1, 2024
    Subspace Embeddings for Khatri-Rao Products (Redux)

selected publications

* denotes equal contribution. See more papers on the dedicated publications page.
  1.  

    UCB Thesis
    Accelerating Multilinear Maps and Structured Sparse Tensor Kernels
    Vivek Bharadwaj
    University of California, Berkeley, 2025

     

    ACDA
    An Efficient Sparse Kernel Generator for O(3)-Equivariant Deep Networks
    Vivek Bharadwaj*, Austin Glover*, Aydın Buluç, James Demmel
    In Proceedings of the Conference on Applied and Computational Discrete Algorithms (ACDA), July 2025

     

    NeurIPS
    Efficient Leverage Score Sampling for Tensor Train Decomposition
    Vivek Bharadwaj*, Beheshteh Rakhshan*, Osman Malik, Guillaume Rabusseau
    In Advances in Neural Information Processing Systems, Dec 2024

     

    NeurIPS
    Fast Exact Leverage Score Sampling from Khatri-Rao Products with Applications to Tensor Decomposition
    Vivek Bharadwaj, Osman Malik, Riley Murray, Laura Grigori, Aydın Buluç, James Demmel
    In Advances in Neural Information Processing Systems, Dec 2023

     

    IPDPS
    Distributed-Memory Sparse Kernels for Machine Learning
    Vivek Bharadwaj, Aydın Buluç, James Demmel
    In 2022 IEEE International Parallel and Distributed Processing Symposium, Jun 2022