The estimation of evolutionary trees (called phylogenies) is an essential step in biological research; however large-scale phylogeny estimation continues to be computationally challenging. Many of the current leading methods are heuristics for NP-hard optimization problems, and these methods typically have limited parallelism for improving scalability to larger numbers of species. In this talk, I …
Abstract: In this talk I will introduce two new subspace models: Mixture Matrix Completion, and Subspace Splitting. Both models are motivated by metagenomics, recommender systems, and dimensionality reduction, and are tightly related to low-rank matrix completion, subspace clustering, robust matched subspace detection, and the maximum feasible subsystem problem. I will …
Many problems in modern statistics can be formulated as an optimization problem with structured constraints, where the constraints often exhibit nonconvexity such as sparsity or low rank. However, working with nonconvex constraints presents challenges from both a theoretical and practical point of view. In this talk, we discuss a convergence …
In this talk, we will consider linear structural equation models which correspond to directed acyclic graphs (DAGs). These models assume that each observed variable is a linear function of the other variables and some error term. It has been previously shown for DAGs, when the error terms in a SEM …
Numerical algebraic geometry uses numerical algorithms to study algebraic varieties, which are sets defined by polynomial equations. It is becoming a core tool in applications of algebraic geometry outside of mathematics. Its fundamental concept is a witness set which gives a representation of a variety that may be manipulated on …
As physics-based simulation has played an increasingly important role in science and engineering, greater demands are being placed on model fidelity. This high fidelity necessitates fine spatiotemporal resolution, which can lead to extreme-scale models whose simulations consume months on thousands of computing cores. Further, most practical decision-making scenarios (e.g., uncertainty …
For many applications in healthcare, econometrics, financial forecasting and climate science, data can only be obtained as aggregates. This begs the question, can one construct accurate models using only aggregates? I will present two vignettes outlining recent work towards an answer. First, consider a sparse linear model learned from IID …
Distributed implementations of popular machine learning algorithms exhibit poor scaling when deployed on more than a few tens of compute nodes. The key sources of this poor performance are communication bottlenecks and straggler nodes in the system. In this talk, I will explain why these bottlenecks are a real challenge …
Given the dramatic successes in machine learning and reinforcement learning over the past half decade, there has been a resurgence of interest in applying these techniques to continuous control problems in robotics, self-driving cars, and unmanned aerial vehicles. Though such applications appear to be straightforward generalizations of standard reinforcement learning, …
In this talk, I will present ongoing work on the knockoff filter for inference in regression. In a high-dimensional model selection problem, we would like to select relevant features without too many false positives. The knockoff filter provides a tool for model selection by creating knockoff copies of each feature, …