Aaditya Ramdas — aramdas [@] cs [dot] cmu [.] edu
8223 Gates (CMU), Pittsburgh

5th Year Joint PhD Student, Machine Learning and Statistics
School of Computer Science, Carnegie Mellon University

My advisors are Larry Wasserman (Stats) and Aarti Singh (ML). My other thesis committee members are Ryan Tibshirani (CMU), Michael Jordan (UC Berkeley) and Arthur Gretton (UC London). I am on the job market. [Curriculum Vitae]


Some Recent Preprints

  1. On The Power of a Nonparametric Two Sample Test in High Dimensions
    Aaditya Ramdas, **Sashank Reddi, Barnabas Poczos, Aarti Singh, Larry Wasserman [pdf]
  2. Fast ADMM Algorithms for Trend Filtering
    Aaditya Ramdas, Ryan Tibshirani [arxiv][R package][talk]
  3. Towards A Deeper Geometric, Analytic and Algorithmic Understanding of Margins
    Aaditya Ramdas, Javier Pena [arxiv]
  4. On The Increasing Power of Kernel Independence Testing due to Stein Shrinkage
    Aaditya Ramdas, **Leila Wehbe [arxiv]
  5. Rows vs Columns for Linear Systems of Equations: Randomized Kaczmarz vs Coordinate Descent
    Aaditya Ramdas [arxiv]

Recent Papers (last 12 months)

  1. On the Decreasing Power of Kernel- and Distance-based Hypothesis Tests in High Dimensions (AAAI '15)
    29th AAAI Conference on Artifical Intelligence, Austin, 2015
    Aaditya Ramdas, **Sashank Reddi, Barnabas Poczos, Aarti Singh, Larry Wasserman [arxiv]
  2. Simultaneously uncovering the patterns of brain regions involved in different story reading subprocesses (PLOS ONE)
    Leila Wehbe, Brian Murphy, Partha Talukdar, Alona Fyshe, Aaditya Ramdas, Tom Mitchell [in press]
  3. Margins, Kernels and Non-linear Smoothed Perceptrons (ICML '14)
    31st International Conference on Machine Learning, Beijing, 2014
    Aaditya Ramdas, Javier Pena [ICML] [pdf] [supp] [20-min oral]
  4. An Analysis of Active Learning with Uniform Feature Noise (AISTATS '14)
    17th International Conference on Artificial Intelligence and Statistics, Reykjavik, 2014
    Aaditya Ramdas, Aarti Singh, Larry Wasserman, Barnabas Poczos [AISTATS] [pdf] [supp] [25-min oral]


Recent Talks and Posters (last 12 months)

  1. Margins: Geometry, Analysis and Algorithms, UCLA IPAM Stochastic Gradient Methods
  2. Increasing Power of Kernel Independence Testing by Stein Shrinkage, UCL-Duke Workshop on High-Dimensional Inference
  3. Decreasing Power of Kernel Hypothesis Testing in High Dimensions, UCL-Duke Workshop on High-Dimensional Inference
  4. A Case for Trend Filtering over Splines, Microsoft Research Cambridge
  5. A Case for Trend Filtering over Splines, Gatsby Neuroscience Unit (UCL)
  6. A Case for Trend Filtering over Splines, ML Lunch Seminar (CMU)
  7. Connecting Convex Optimization and Active Learning, IIT Madras
  8. Connecting Convex Optimization and Active Learning, IBM Research Bangalore
  9. Connecting Convex Optimization and Active Learning, Chennai Math. Institute

Reviewing
  1. Journal of Machine Learning Research
  2. Biometrika
  3. Computational Optimization and Applications
  4. Neural Information Processing Systems
  5. International Conference on Machine Learning

Miscellaneous
  1. Co-organizing NIPS OPT 2014 - Workshop on Optimization in ML.
  2. Made pre-requisite review videos for CMU's graduate courses in ML.