Aggregation using Nuclear Norm Regularization. We study a version of the problem known as collaborative ranking. Statistical Science, 27(4 538-557, December, 2012. By establishing these conditions with high probability for numerous statistical models, our analysis applies to a wide range of M-estimators, including sparse linear regression using Lasso; group Lasso for block sparsity; log-linear models with regularization; low-rank matrix recovery using nuclear norm regularization; and matrix decomposition. Learning Sparse Boolean Polynomials. I am currently an Assistant Professor in the Department of Statistics and Data Science at Yale University. Monthly Notices of the Royal Astronomical Society 435 (2, 2013). "Restricted Strong Convexity Implies Weak Submodularity.". Fast global convergence of gradient methods for high-dimensional statistical recovery. Estimation of (near) low-rank matrices with noise and high-dimensional scaling. Presented in part at nips Conference, December 2010.
His work borrows from and improves upon tools of statistical signal processing, machine learning, probability and convex optimization. Prior to that I worked with Prof. The focus of my research is to develop theoretically sound methods, which are both computationally and statistically efficient, for extracting information from large datasets. Journal of Machine Learning Research, 13:, May 2012.
Presented in part at nips Workshops, Vancouver, Canada, December 2010. Devavrat Shah at MIT as a postdoc and Prof. Iterative Ranking from Pair-wise Comparisons. To be presented at cikm, 2012. We provide a theoretical justification for a nuclear norm regularized optimization procedure, and provide high-dimensional scaling results that show how the error in estimating user preferences behaves as the number of observations increase. CircCQQ, circulation: Cardiovascular Quality and Outcomes, 2016. "Sparse interpretable estimators for cyclic arrival start college essay with a quote rates.". A salient feature of his work has been to understand how hidden low-complexity structure in large datasets can be used to develop computationally and statistically efficient methods for extracting meaningful information for high-dimensional estimation problems. Nips, 2012 in Lake Tahoe. Stochastic optimization and sparse statistical recovery: An optimal algorithm for high dimensions.