Aniket Das

About Me

Hi! I’m a first year PhD student in the CS Theory Group at Stanford. My interests broadly lie at the intersection of probability and theoretical computer science. Less broadly, I like thinking about Markov Chains, the complexity of statistical inference, and algorithmic applications of Wasserstein Gradient Flows.

Prior to grad school, I was a Pre-Doctoral Researcher at Google DeepMind. Even earlier, I was a dazed and confused undergrad at Indian Institute of Technology Kanpur, where I double majored in Electrical Engineering and Math.

Selected Publications

• Near-Optimal Streaming Heavy-Tailed Statistical Estimation with Clipped SGD
  with Dheeraj Nagaraj, Soumyabrata Pal, Arun Suggala and Prateek Varshney
  NeurIPS 2024 [Paper]

• Provably Fast Finite-Particle Variants of SVGD via Virtual Particle Stochastic Approximation
  with Dheeraj Nagaraj
  Spotlight at NeurIPS 2023 [Paper]
  Oral Presentation at OTML Workshop, NeurIPS 2023

• Utilising the CLT Structure in Stochastic Gradient based Sampling : Improved Analysis and Faster Algorithms
  with Dheeraj Nagaraj and Anant Raj
  COLT 2023 [Paper]

• Near Optimal Heteroscedastic Regression with Symbiotic Learning
  with Dheeraj Baby, Dheeraj Nagaraj and Praneeth Netrapalli
  COLT 2023 [Paper]

• Sampling without Replacement Leads to Faster Rates in Finite-Sum Minimax Optimization
  with Bernhard Schölkopf and Michael Muehlebach
  NeurIPS 2022 [Paper]

Talks

• Linear Time Streaming Algorithms for Heavy Tailed Statistics
  MSR IISc Theory Seminar 2024 Slides

• Sampling Through the Lens of Optimization : Recent Advances and Insights
  MSR IISc Theory Seminar 2023, EPFL FLAIR Seminar 2024 Slides

Service

• Reviewer : NeurIPS, AISTATS
• Co-ordinator : Special Interest Group in Machine Learning, IIT Kanpur
• Undergrad Mentor : Programming Club, IIT Kanpur and Stamatics (Math Club), IIT Kanpur

Powered by Jekyll and Minimal Light theme.