Seminar: Lijun Ding, Univ. Wisconsin and Washington
1:00-2:00pm in ANGU 241 (Henry Angus).
Title: Optimization for statistical learning with low dimensional structure: regularity and conditioning
You can sign up for email announcements of seminars by joining the mailing list at this link: http://eepurl.com/h7A_Iv
1:00-2:00pm in ANGU 241 (Henry Angus).
Title: Optimization for statistical learning with low dimensional structure: regularity and conditioning
3:00pm-4:00pm in Mathx 1100 (Math Annex). Tea at 2:15pm.
Title: Semidefinite programming in data science: strict complementarity and storage optimal algorithms
3:00pm-4:00pm in ESB 2012 (Earth Sciences Building)
Title: Statistical and Computational Phenomena in Deep Learning
1:00-2:00pm in ANGU 241 (Henry Angus)
Title: Implicit regularization and benign overfitting for neural networks in high dimensions
PhD student, Oxford University
Assistant Professor, Concordia University
Associate Professor, Michigan State University
Stochastic Bin Packing with Time-Varying Item Sizes
Structured bandits meets classification: the thresholded linear bandits problem
Log-concave Density Estimation in Undirected Graphical Models
Neural Tangent Kernels
Title: Noisy Sorting Capacity
Abstract: We study the sorting problem in the presence of noise. Unlike the common approach in the literature which aims to minimize the number of pairwise comparisons m to achieve a given desired error probability, our goal is to characterize the maximal ratio (n log n)/m such that the ordering of the elements can be estimated with a vanishing error probability asymptotically.
Theoretical bounds for low-rank projection, and the matrix Bernstein inequality
Contact: Harvey
Contact: Sutherland
Contact: Robeva