Special year - math workshop

Mar 18 2020

Low Algebraic Dimension Matrix Completion

Speaker: Laura Balzano
4:30pm | West Building Lecture Hall
Low rank matrix completion (LRMC) has received tremendous attention in recent years.  The low rank assumption means that the columns (or rows) of the matrix to be completed are points on a low-dimensional linear variety.  This work extends this thinking to cases where the columns are points on...
Mar 18 2020

Tea Break

4:00pm | Fuld Hall Common Room
Mar 18 2020

Low-rank matrix recovery from quantized or count observations

Speaker: Mark Davenport
3:00pm | West Building Lecture Hall
Low-rank matrices play a fundamental role in modeling and computational methods for signal processing and machine learning. In many applications where low-rank matrices arise, these matrices cannot be fully sampled or directly observed, and one encounters the problem of recovering the matrix...
Mar 18 2020

What is the role of curvature in complexity of optimization on manifolds?

Speaker: Nicolas Boumal
2:00pm | West Building Lecture Hall
Low rank is a popular prior in matrix and tensor completion. The set of matrices or tensors of a given rank forms a smooth manifold. Estimating the full data under the low-rank prior then turns into an optimization problem over a manifold of fixed-rank objects. What is the worst-case complexity...
Mar 18 2020


12:30pm | Simons Hall Dining Hall
Mar 18 2020

High-dimensional omics data analysis with missing values

Speaker: Anru Zhang
11:45am | West Building Lecture Hall
We have seen the rise of high-dimensional omics data, e.g., genome, transcriptome, microbiome, and proteome in recent decades. The different types of missingness in modern omics data bring up significant biological and statistical challenges. In this talk, we focus on two problems in modern...
Mar 18 2020

Learning with aggregated data; a tale of two approaches

Speaker: Sanmi Koyejo
10:45am | West Building Lecture Hall
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,...
Mar 18 2020


10:15am | West Building Lecture Hall
Mar 18 2020

Metric and manifold repair for missing data

Speaker: Anna Gilbert, Keynote 4
9:15am | West Building Lecture Hall
For many machine learning tasks, the input data lie on a low-dimensional manifold embedded in a high-dimensional space and, because of this high-dimensional structure, most algorithms inefficient. The typical solution is to reduce the dimension of the input data using a standard dimension...
Mar 17 2020

Poster Session

Speaker: Various
4:00pm | Simons Hall Dining Hall