Multivariate Power Laws and Preferential Attachment Modeling In one-dimension, heavy tails or power-laws are easily understood to represent Pareto like behavior where data plotted on a log-log scale looks roughly linear. The generalization to higher dimensions is not always obvious … Read more
Survey Descent: A Multipoint Generalization of Gradient Descent for Nonsmooth Optimization First-order minimization algorithms, which rely only on blackbox (sub)gradient oracles, have always played a central role in the field of optimization, and are now even more prominent due to … Read more
Multivariate Power Laws and Preferential Attachment Modeling In one-dimension, heavy tails or power-laws are easily understood to represent Pareto like behavior where data plotted on a log-log scale looks roughly linear. The generalization to higher dimensions is not always obvious … Read more
From HeartSteps to HeartBeats: Personalized Decision-making Ever-increasing access to data and computational power allows us to make decisions that are personalized to users by taking their behaviors and contexts into account. These developments are especially useful in domains like mobile … Read more
On the Computational Complexity of Semidefinite and Polynomial Optimization: A real Algebraic Geometry Approach Semidefinite and polynomial optimization (SDO and PO) are topics of great theoretical and practical interest, with numerous applications in theoretical computer science, control theory, and statistics. … Read more
Multivariate Power Laws and Preferential Attachment Modeling In one-dimension, heavy tails or power-laws are easily understood to represent Pareto like behavior where data plotted on a log-log scale looks roughly linear. The generalization to higher dimensions is not always obvious … Read more
Statistical Thresholds for Tensor PCA Recent work in theoretical physics has produced numerous conjectures linking problems in high- dimensional statistics to the behavior of disordered magnetic materials known as spin glasses. In this talk, I will discuss results from joint … Read more
Multivariate Power Laws and Preferential Attachment Modeling In one-dimension, heavy tails or power-laws are easily understood to represent Pareto like behavior where data plotted on a log-log scale looks roughly linear. The generalization to higher dimensions is not always obvious … Read more
On the Interplay of Optimal Transport and Distributionally Robust Optimization Optimal Transport (OT) seeks the most efficient way to morph one probability distribution into another one, and Distributionally Robust Optimization (DRO) studies worst-case risk minimization problems under distributional ambiguity. It … Read more
To Adjust or not to Adjust? Estimating the Average Treatment Effect in Randomized Experiments with Missing Covariates Randomized experiments allow for consistent estimation of the average treatment effect based on the difference in mean outcomes without strong modeling assumptions. Appropriate … Read more
Multivariate Power Laws and Preferential Attachment Modeling In one-dimension, heavy tails or power-laws are easily understood to represent Pareto like behavior where data plotted on a log-log scale looks roughly linear. The generalization to higher dimensions is not always obvious … Read more
Universality of regularized regression estimators in high dimensions The study of regularized regression estimators is of fundamental importance in high dimensional inference. From the canonical linear model to many of its extensions, a by now well-established type of analysis has … Read more
