Akshay Kumar

Email: kumar511@umn.edu I am seeking a postdoctoral position. Please contact me if you have an opening.

About me

I'm currently pursuing my Ph.D. in the Electrical and Computer Engineering department at University of Minnesota Twin Cities, where I am advised by Jarvis Haupt. My research interests are in machine learning and optimization, particularly on deep learning theory. Before starting my Ph.D., I received my B.Tech.-M.Tech. (Dual Degree) in Electrical Engineering from Indian Institute of Technology Kanpur.

Publications

• Towards Understanding Gradient Flow Dynamics of Homogeneous Neural Networks Beyond the Origin
  Akshay Kumar and Jarvis Haupt.
  Preprint

• Early Directional Convergence in Deep Homogeneous Neural Networks for Small Initializations
  Akshay Kumar and Jarvis Haupt.
  Accepted at TMLR.

• Directional Convergence Near Small Initializations and Saddles in Two-Homogeneous Neural Networks
  Akshay Kumar and Jarvis Haupt.
  Accepted at TMLR.

• Convexifying Sparse Interpolation With Infinitely Wide Neural Networks: An Atomic Norm Approach
  Akshay Kumar and Jarvis Haupt.
  IEEE Signal Processing Letters, 2020

• Group Sparsity via Implicit Regularization for MIMO Channel Estimation
  Akshay Kumar, Akshay Malhotra and Shahab Hamidi-Rad.
  IEEE Conference on Wireless Communications and Networking, 2023

• Hybrid Maximum Depth-kNN Method for Real Time Node Tracking using Multi-Sensor Data
  Sudhir Kumar, Abhay Kumar, Akshay Kumar and Rajesh Hegde.
  IEEE International Conference on Communications (ICC) 2015