Avatar

Ramchandran Muthukumar

PhD Student

Johns Hopkins University

Biography

I am a first year PhD Student in the Computer Science Department at Johns Hopkins University. I am fortunate to be advised by Professor Jeremias Sulam. My research interests revolve around theoretical questions in machine learning and robustness gaurantees. I am also interested in exploiting structure in data to develop efficient algorithms (eg. sparsity, low rank).

Prior to starting my graduate studies, I was a research assistant at ORIE Department at Cornell where I was supervised by Professor Madeleine Udell. My work at Cornell involved developing low-memory algorithms for PDE-optimization (in collaboration with Dr. Drew Kouri of Sandia National Laboratories).

Interests

  • Theoretical Machine Learning
  • Adversarial Robustness
  • Sparse Coding
  • Optimization

Education

  • PhD in Computer Science (in progress)

    Johns Hopkins University

  • MSc in Mathematics, 2018

    BITS Pilani

  • B.E. in Computer Science, 2018

    BITS Pilani

Recent Posts

Adversarial Robust Generalization requires more data (Schmidt et. al)

Trial post to see if I can blog my notes Mathematical Setup Standard Classification Error Let $\mathcal{P} : \mathbb{R}^d\times {-1,+1} …

Recent Publications

  • Randomized Sketching Algorithms for Low-Memory Dynamic Optimization
    R. Muthukumar, D. Kouri and M.Udell
    Submitted, 2019

Contact

  • Malone Hall 245, Johns Hopkins University, Baltimore, MD, 21218, United States