I am a senior PhD student in the Electrical and Computer Engineering Department, Rice University. I work with Prof. Anshumali Shrivastava in the RUSHLAB. My primary research area is Extreme Scale Deep Learning using Randomized Hashing methods.

I previously interned as an Applied Scientist at Amazon Search, Palo Alto from May 2018 - Aug 2019 and again during May 2020 - Aug 2020. I worked on a myriad of problems like query to product prediction, super-fast reformulation for zero result queries, query-category prediction and fast approximate nearest neighbor search.

I received my Bachelor of Technology (B.Tech.) in Electrical Engineering (2011-2015) from Indian Institute of Technology, Bombay.

Here is my resume.

Updates:

  • Our paper A Tale of Two Efficient and Informative Negative Sampling Distributions was accepted for a long talk at ICML 2021.
  • Our paper SOLAR: Sparse Orthogonal Learned and Random Embeddings was accepted to ICLR 2021. pdf poster
  • Our paper Fast Processing and Querying of 170TB of Genomics Data via a Repeated And Merged BloOm Filter (RAMBO) was accepted to SIGMOD 2021.
  • Our paper SDM-Net: A Simple and Effective Model for Generalized Zero-Shot Learning was accepted to UAI 2021.
  • Received the Ken Kennedy Institute BP Fellowship for 2020-21.
  • We presented our paper SLIDE : In Defense of Smart Algorithms over Hardware Acceleration for Large-Scale Deep Learning Systems at MLSys 2020, Austin. pdf video package
  • We presented our paper Extreme Classification in Log Memory using Count-Min Sketch: A Case Study of Amazon Search with 50M Products at NeurIPS 2019, Vancouver. pdf poster video package
  • Received American Society of Indian Engineers (ASIE) scholarship for 2019.
  • We presented 4 papers in NeurIPS 2019 workshops. Please refer to Publications for a list of all papers.

In the News:

  • An algorithm could make CPUs a cheap way to train AI Endgadget article
  • Deep Learning breakthrough made by Rice University scientists ARS Technica article
  • SLIDE algorithm for training deep neural nets faster on CPUs than GPUs InsideHPC article
  • Hash Your Way To a Better Neural Network IEEE Spectrum article.
  • Deep learning rethink overcomes major obstacle in AI industry TechXplore article
  • Researchers report breakthrough in ‘distributed deep learning’ TechXplore article.

Invited Talks

  • Jane Street Symposium 2020, New York on Jan 13th.
  • Spotlight talk at Systems for ML workshop at NeurIPS 2019 on SLIDE : Training Deep Neural Networks with Large Outputs on a CPU faster than a V100-GPU. video pdf package
  • ‘Intro to Actor-Critic Methods and Imitation in Deep Reinforcement Learning’ at Houston ML Meetup, University of Houston on Dec 7th.
  • ‘Intro to Imitation Learning’ at Schlumberger, Katy, TX on Nov 19th.
  • Imitate like a Baby:The Key to Efficient Exploration in Deep Reinforcement Learning at BioScience Research Collaborative (BRC) in Rice Data Science Conference on Oct 14th. video pdf