Jul 2024: Amazing experience presenting our four papers in the Mechanistic Interpretability and Theoretical Foundations of Foundation
Models workshops at ICML 2024: Fundamental limits of prompt compression, Attention with Markov,
Local to Global, and Constant depth suffices.
Mar 2024: Talk on Attention with Markov at ETH Zürich hosted by Thomas Hofmann.
Feb 2024: Our new work on principled analysis of transformers is now available on arXiv: Attention with Markov.
Dec 2023: Talks at UC Berkeley and Stanford on LASER.
Nov 2023: Our recent work LASER is accepted for the Oral track at the NeurIPS Federated Learning Workshop, 2023.
Apr 2023: Our paper CRISP is accepted in ICML, 2023.
Oct 2022: Talk at ETH Zurich on KO codes.
Aug 2022: Talks at TIFR, IIT Bombay, IISc, and IIT Madras on KO codes.
Aug 2022: Talk on KO codes at University of Toronto.
May 2022: I have accepted a postdoctoral position at EPFL with Prof. Michael Gastpar. Switzerland here I come.
Mar 2022: Defended my thesis! Officially a doctor who can't write prescriptions.
Nov 2021 - June 2022: Talks at MIT, UC Berkeley, CMU, UIUC, UCSD, EPFL, and IST Austria on KO codes.
Oct 2021: Gave a talk on KO codes at ISL Colloquium, Stanford.
May 2021: Our paper KO codes is accepted in ICML, 2021. Spent almost 1.5 years solely working on this project. So glad it got accepted in the very first attempt. Yay!
May 2020: Our paper Optimal transport mapping via Input-Convex-Neural-Networks is accepted in ICML, 2020.
Jan 2020: Our paper Learning in Gated Neural Networks is accepted in AISTATS, 2020.
Jan 2020: Talk on ‘‘Learning in Gated Neural Networks’’ at IIT Madras, Microsoft Research-Bangalore, Indian Institute of Science, Tata Institue of Fundamental Research, IIT Bombay.
July 2019: Honored to be a recepient of the Best Paper Award at ACM MobiHoc 2019.
Apr 2019: Our paper Breaking the gridlock in Mixture-of-Experts: Consistent and Efficient Algorithms is accepted in ICML, 2019.
Mar 2019: I am honored to be a recepient of the prestigious Joan and Lalit Bahl Fellowship from the ECE department for the academic year 2019-20.
Dec 2018: Our paper arXiv Learning One-hidden-layer Neural Networks under General Input Distributions is accepted in AISTATS, 2019.
Oct 2018: Talk on ‘‘Learning in Gated Neural Networks" at UC Berkeley and University of Washington.
Mar 2018: I am honored to be awarded the Sundaram Seshu International Student Fellowship for the academic year 2018-19.
Mar 2018: Our team is a finalist for the prestigous Qualcomm Innovation Fellowship 2018-US.
Mar 2018: Talk on ‘‘Globally Consistent Algorithms for Mixture-of-Experts’’ at SINE seminar (UIUC).
Feb 2018: Our paper on Mixture-of-Experts is now available on arXiv.
Jul 2016: Talk at ISIT 2016, Barcelona on Equivalence of Shannon and differential entropy inequalities.