(my philosophy: academic honesty for websites includes avoiding being misleading to an outsider; this involves declaring which papers were double or single blind peer-reviewed at conferences/journals with low acceptance rates, as opposed to being "refereed" or "invited" for submission at places with high acceptance rates; it also includes declaring on which work you are a primary contributor of content, where you know and can discuss the paper details confidently if contacted)

* indicates a paper on which I was one of the primary contributors, ** indicates an equally contributing student author

Peer-reviewed Publications

longer papers, lower acceptance rates

  • *Margins, Kernels and Non-linear Smoothed Perceptrons (ICML '14)
    The 31st International Conference on Machine Learning, Beijing, 2014
    A.R., Javier Pena [ICML] [pdf] [supp] [20-min oral] [abs]

  • *An Analysis of Active Learning with Uniform Feature Noise (AISTATS '14)
    17th International Conference on Artificial Intelligence and Statistics, Reykjavik, 2014
    A.R., Aarti Singh, Larry Wasserman, Barnabas Poczos [AISTATS] [pdf] [supp] [25-min oral] [abs]

  • *Algorithmic Connections Between Active Learning and Stochastic Convex Optimization (ALT '13)
    The 24th International Conference on Algorithmic Learning Theory, Singapore, 2013
    A.R., Aarti Singh [ALT] [pdf] [25-min oral] [abs]

  • *Optimal Rates for Stochastic Convex Optimization using Tsybakov's Noise Condition (ICML '13)
    The 30th International Conference on Machine Learning, Atlanta, 2013
    A.R., Aarti Singh [arxiv] [ICML] [pdf] [supp] [20-min oral] [abs]

Preprints

  • *Regularized Brain Reading with Shrinkage and Smoothing
    Leila Wehbe, A.R., Rebecca Steorts, Cosma Shalizi [arxiv]

  • *Towards A Deeper Geometric, Analytic and Algorithmic Understanding of Margins
    A.R., Javier Pena [arxiv]

  • Predicting Brain Activity during Story Processing
    Leila Wehbe, Brian Murphy, Partha Talukdar, Alona Fyshe, A.R., Tom Mitchell

  • *Stein Shrinkage for Cross-Covariance Operators and Kernel Independence Testing
    A.R., **Leila Wehbe [arxiv]

  • *Rows vs Columns for Linear Systems of Equations: Randomized Kaczmarz vs Coordinate Descent
    A.R. [arxiv]

  • *Fast ADMM Algorithms for Trend Filtering
    A.R., Ryan Tibshirani [arxiv]

  • *Kernel MMD, Median Heuristic and Distance Correlation in High Dimensions
    A.R., **Sashank Reddi, Barnabas Poczos, Aarti Singh, Larry Wasserman [arxiv]

Refereed Publications

shorter papers, higher acceptance rates

  • *Exploring the Intersection of Active Learning and Stochastic Convex Optimization
    1st IEEE Global Conference on Signal and Information Processing, Austin, 2013
    A.R., Aarti Singh [IEEE]

  • *Unifying Stohcastic Convex Optimization and Active Learning
    6th NIPS Workshop on Optimization for Machine Learning, Lake Tahoe, 2013
    A.R., Aarti Singh [NIPS][20-min talk]