Advait Parulekar
Scholar

Advait Parulekar

Google Scholar ID: 9u8SExAAAAAJ
Graduate Student
Machine Learning
Citations & Impact
All-time
Citations
165
 
H-index
6
 
i10-index
6
 
Publications
10
 
Co-authors
13
list available
Resume (English only)
Academic Achievements
  • Efficient Approximate Posterior Sampling with Annealed Langevin Monte Carlo
  • In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness (NeurIPS 2024, Spotlight)
  • InfoNCE Loss Provably Learns Cluster-Preserving Representations (COLT 2023)
  • A Theoretical Justification for Image Inpainting using Denoising Diffusion Probabilistic Models
  • PAC Generalization via Invariant Representations (ICML 2023)
  • Improved Algorithms for Misspecified Linear Markov Decision Processes (AISTATS 2022)
  • Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation (ICML 2022)
  • L1 Regression with Lewis Weights Subsampling (RANDOM 2021)
  • Stochastic Linear Bandits with Protected Subspace
  • Locating conical degeneracies in the spectra of parametric self-adjoint matrices (SIAM Journal on Matrix Analysis and Applications, Volume 42)
  • Honorable Mention, 2018 William Lowell Putnam Math Contest
  • USA Physics Olympiad Team Member, 2015
  • Indian Math Olympiad Training Camp, 2013