• Click on the titles of individual talks for abstract, slides and archived video.

All events take place in the main auditorium, Calvin Lab, with the exception of the Open Lecture on Wednesday afternoon, which takes place in the Banatao Auditorium, Sutardja-Dai Hall.

–
Coffee and Check-In
–
Opening Remarks
–
Variational Inference: Foundations and Innovations
David Blei, Columbia University
–
Break
–
Representational and Optimization Properties of Deep Residual Networks
Peter Bartlett, UC Berkeley
–
Composing Graphical Models with Neural Networks for Structured Representations and Fast Inference
David Duvenaud, University of Toronto
–
Lunch
–
Scaling Up Bayesian Inference for Big and Complex Data
David Dunson, Duke University
–
Unbiased Estimation of the Spectral Properties of Large Implicit Matrices
Ryan Adams, Harvard University
–
Break
–
Stochastic Gradient MCMC for Independent and Dependent Data Sources
Emily Fox, University of Washington
–
Reception
–
Coffee and Check-In
–
On Gradient-Based Optimization: Accelerated, Distributed, Asynchronous and Stochastic
Michael Jordan, UC Berkeley
–
Break
–
Sampling Polytopes: From Euclid to Riemann
Yin Tat Lee, Microsoft Research and University of Washington
–
Understanding Generalization in Adaptive Data Analysis
Vitaly Feldman, IBM Almaden
–
Lunch
–
Gradient Descent Learns Linear Dynamical Systems
Moritz Hardt, Google
–
Your Neural Network Can't Learn Mine
John Wilmes, Georgia Institute of Technology
–
Break
–
Efficient Distributed Deep Learning Using MXNet
Anima Anandkumar, UC Irvine
–
Coffee and Check-In
–
Machine Learning for Healthcare Data
Katherine Heller, Duke University
–
Break
–
Machine Learning Combinatorial Optimization Algorithms
Dorit Hochbaum, UC Berkeley
–
A Cost Function for Similarity-Based Hierarchical Clustering
Sanjoy Dasgupta, UC San Diego
–
Lunch
–
The Imitation Learning View of Structured Prediction
Hal Daume, University of Maryland at College Park
–
Exponential Computational Improvement by Reduction
John Langford, Microsoft Research New York
–
Break
–
Simons Institute Open Lecture: "Does Computational Complexity Restrict Artificial Intelligence (AI) and Machine Learning?
Sanjeev Arora (Princeton University)
–
Coffee and Check-In
–
Embedding as a Tool for Algorithm Design
Le Song, Georgia Institute of Technology
–
Break
–
Robust Estimation of Mean and Covariance
Anup Rao, Georgia Institute of Technology
–
Computational Efficiency and Robust Statistics
Ilias Diakonikolas, University of Southern California
–
Lunch
–
System and Algorithm Co-Design, Theory and Practice, for Distributed Machine Learning
Eric Xing, Carnegie Mellon University
–
The Polytope Learning Problem
Navin Goyal, Microsoft Research
–
Break
–
Computational Challenges and the Future of ML Panel
–
Coffee and Check-In
–
Computationally Tractable and Near Optimal Design of Experiments
Aarti Singh, Carnegie Mellon University
–
Break
–
Learning from Untrusted Data
Gregory Valiant, Stanford University
–
The “Tell Me Something New” Model of Computation for Machine Learning
Yoav Freund, UC San Diego
–
A Survey of Dependent Rounding
Aravind Srinivasan