Time 
Speaker 
Title 
Links 
7:30  7:40am 
Organizers 
Introduction and Poster Setup 
[ Slides ] [ Video ] 
7:40  8:20am 
Robert M. Freund 
Remarks on FrankWolfe and Structural Friends 
[ Slides ] [ Video ] 
8:20  9:00am 
Ben Recht 
The Algorithmic Frontiers of Atomic Norm Minimization: Relaxation, Discretization, and Greedy Pursuit 
[ Slides ] [ Video ] 
9:00  9:30pm 
Coffee Break 
9:30  9:45am 
Nikhil Rao, Parikshit Shah and Stephen Wright 
Conditional Gradient with Enhancement and Truncation for Atomic Norm Regularization 
[ Slides ] [ Video ] 
9:45  9:55am

Hector Allende, Emanuele Frandi, Ricardo Nanculef, Claudio Sartori 
Pairwise Away Steps for the FrankWolfe Algorithm 

9:55  10:05am 
Simon LacosteJulien and Martin Jaggi 
An Affine Invariant Linear Convergence Analysis for FrankWolfe Algorithms 
[ Slides ] [ Video ] 
10:05  10:15am 
Vamsi Potluru, Jonathan Le Roux, Barak Pearlmutter, John Hershey and Matthew Brand 
Coordinate Descent for mixednorm NMF

[ Slides ] [ Video ] 
10:15  10:30am 
Robert M. Freund and Paul Grigas 
New Analysis and Results for the Conditional Gradient Method 
[ Slides ] [ Video ] 
10:30  3:30pm 
Lunch Break 
3:30  3:45pm 
Marguerite Frank 
Honorary Guest 
[ Video ] 
3:45  4:25pm 
Shai ShalevSchwartz 
Efficiently Training SumProduct Neural Networks using Forward Greedy Selection 
[ Slides ] [ Video ] 
4:25  4:40pm 
Xiaocheng Tang and Katya Scheinberg 
Complexity of Inexact Proximal Newton Methods 
[ Slides ] [ Video ] 

Vladimir Temlyakov 
From Greedy Approximation to Greedy Optimization 
[ Slides ] 
4:40  4:50pm 
Jacob Steinhardt and Jonathan Huggins 
A Greedy Framework for FirstOrder Optimization 
[ Slides ] [ Video ] 
4:50  5:00pm 
Ahmed Farahat, Ali Ghodsi and Mohamed Kamel 
A Fast Greedy Algorithm for Generalized Column Subset Selection 
[ Slides ] [ Video ]
[ Poster ] 
5:00  5:30pm 
Coffee Break 
5:30  6:10pm 
Francis Bach 
Conditional Gradients Everywhere 
[ Slides ] [ Video ] 
6:10  6:25pm 
David Belanger, Dan Sheldon and Andrew McCallum 
Marginal Inference in MRFs using FrankWolfe 
[ Slides ] [ Video ] 



