TTIC is having a weekly seminar series presenting the research currently underway at the Institute. Every week a different TTIC faculty member will present their research.

The lectures are intended both for students seeking research topics and advisers, and for the general TTIC and University of Chicago communities interested in hearing what their colleagues are up to.

To receive announcements about the seminar series, please subscribe to the mailing list.

For additional questions, contact Nati Srebro (

Title: The Complexity of Minimizing Individual Convex Functions

Date: June 10, 2016

Speaker: John Lafferty

Title: Dense Correspondences in the Era of Deep Learning

Date: June 3, 2016

Speaker: Qixing Huang

Title: Complexity of Semi-Algebraic and Algebraic Proofs

Date: May 27, 2016

Speaker: Alexander Razborov

Title: On the Approximability of Constraint Satisfaction Problems

Date: May 20, 2016

Speaker: Madhur Tulsiani

Title: Optimization and tightness of convex relaxations for structured output prediction

Date: May 13, 2016

Speaker: Ofer Meshi

Title: Satisfiability of Ordering CSPs Above Average

Date: Apr 22, 2016

Speaker: Yury Makarychev

Title: Learning Concise Representations of Textual Knowledge

Date: Apr 8, 2016

Speaker: Kevin Gimpel

Title: Fast and Simple PCA via Convex Optimization

Date: Feb 26, 2016

Speaker: Dan Garber

Title: Toward Neural Segmental Sequence Models

Date: Feb 5, 2016

Speaker: Karen Livescu

Title: Architectures for Learning in Low-level Vision Applications

Date: Jan 29, 2016

Speaker: Ayan Chakrabarti

Title: Affinity CNN: Learning Pixel-Centric Pairwise Relations for Figure/Ground Embedding

Date: Jan 22, 2016

Speaker: Michael Marie

Title: Stochastic optimization with exponentially concave losses: lower and upper bounds on the excess risk

Date: Jan 15, 2016

Speaker: Mehrdad Mahdavi

Title: Dense Correspondences in the Era of Deep Learning

Date: Jan 8, 2016

Speaker: Qixing Huang

Title: Rich Representations for Parsing Visual Scenes

Date: Nov 13, 2015

Speaker: Greg Shakhnarovich

Title: An Average-Case Depth Hierarchy Theorem for Boolean Circuits

Date: Nov 6, 2015

Speaker: Li-Yang Tan

Title: Distributed machine learning

Date: Oct 30, 2015

Speaker: Huy Nguyen

Title: Dropping Convexity for Faster Semi-definite Optimization

Date: Oct 23, 2015

Speaker: Srinadh Bhojanapalli

Title: Learning and Optimization: Deep and Distributed

Date: Oct 16, 2015

Speaker: Nathan Srebro

Title: Improved 3d structure prediction of beta-barrel membrane proteins using evolutionary coupling constraints and a reduced state space

Date: Oct 9, 2015

Speaker: Hammad Naveed