Puneesh Deora

Hi, I'm Puneesh! I am an MASc student at UBC, fortunate to be advised by Prof. Christos Thrampoulidis. I am broadly interested in understanding foundations of deep learning optimization and generalization.

I received my Bachelor's from IIT Roorkee in ECE, where I had the good fortune to receive guidance from Prof. Saumik Bhattacharya and Prof. P.M. Pradhan . My undergrad research was mainly focused on GANs for compressed sensing MRI reconstruction.

Email | Google Scholar | CV | Github

selected papers

(* denotes equal contribution)

  1. Implicit Bias and Convergence Rates for Self-attention
    Bhavya Vasudeva*, Puneesh Deora*, and Christos Thrampoulidis.
    Preprint.
  1. On the Optimization and Generalization of Multi-head Attention
    Puneesh Deora*, Rouzbeh Ghaderi*, Hossein Taheri*, and Christos Thrampoulidis.
    Workshop on High-dimensional Learning Dynamics, ICML 2023. (Under review)
  1. Fast Test Error Rates for Gradient-based Algorithms on Separable Data
    Puneesh Deora*, Bhavya Vasudeva*, Vatsal Sharan, Christos Thrampoulidis.
    Workshop on High-dimensional Learning Dynamics, ICML 2023 and ICASSP 2024.