CSL SINE Group
54 matches found
SINE seminar on Monday, March 27th, 4:00 p.m.: "Learning with Aggregated Data; a Tale of Two Approaches", Dr. Sanmi Koyejo, Assistant Professor, Department of Computer Science at Illinois
“Distributed Newton Method for Large Scale Optimization”, Rasul Tutunov, Computer and Information Science, University of Pennsylvania Rasul Tutunov received his B.Sc. and M.A.Sc. in Physics and Applied Mathematics in 2007 and 2009 from Moscow Institute of Physics and Technology. Currently he is a 5 year PhD student at the Computer and Information Science Dept. at U-Penn.
“Accelerating Stochastic Gradient Descent", Praneeth Netrapalli, Microsoft Research India Praneeth is currently a researcher at MR India. Prior to that, he spent two years as a postdoc at Microsoft Research New England. He received his PhD from UT Austin in 2014 under the guidance of Sujay Sanghavi, and B-Tech from IIT Bombay in 2007, all in electrical engineering.
TITLE: “Regularization in non-convex optimization” SPEAKER: Suriya Gunasekar Research Assistant Professor Toyota Technological Institute at Chicago DATE: Monday, April 10, 2017 TIME: 4:00 pm LOCATION: 141 CSL
TITLE: “Aligning and Assembling Networks without Labels” SPEAKER: Matthias Grossglauser, Ph.D., Associate Professor, School of Computer and Communication Sciences, École polytechnique fédérale de Lausanne (EPFL) DATE: Wednesday, April 19, 2017 TIME: 4:00 pm LOCATION: 141 CSL
SINE Seminar on ERM and the analysis of optimization methods like SGD, SAG ,Finito, SDCA, and SVRG, and their derived LMI's.
TITLE: "Multi-Frame Super-Resolution Imaging" SPEAKER: Eric Shields Optical Engineer Sandia National Laboratories
Sai-Kit Yeung, Assistant Professor at the Singapore University of Technology and Design (SUTD), will give a talk on "Data-driven Computer Graphics Modeling" on Friday, December 15, 2017 at 10:00 a.m. in Room 141 CSL.
SINE seminar series on Monday, October 8, 4 p.m.
ABSTRACT: Isotonic regression is a standard problem in shape-constrained estimation where the goal is to estimate an unknown nondecreasing regression function $f$ from independent pairs $(x_i, y_i)$ where $E[y_i]=f(x_i), i=1, \ldots n$. While this problem is well understood both statistically and computationally, much less is known about its uncoupled counterpart where
Fall 2019 CSL SINE Seminar
Each year, the Allerton Conference draws some of the brightest minds from industry, academia and government to discuss innovation in the fields of communication, control and computing. We invite you to submit your work and join us at Allerton Park and Retreat Center for an exciting few days of presentations, special events and networking.