Simons Institute (videos of May 2017)

source: Simons Institute
43:14 Learning from Untrusted Data Gregory Valiant, Stanford University
Computational Challenges in Machine Learning
https://simons.berkeley.edu/talks/gregory-valiant-2017-5-4
41:35 The “Tell Me Something New” Model of Computation for Machine Learning Yoav Freund, UC San Diego
Computational Challenges in Machine Learning
https://simons.berkeley.edu/talks/yoav-freund-2017-5-1
1:03:16 Computationally Tractable and Near Optimal Design of Experiments Aarti Singh, Carnegie Mellon University
Computational Challenges in Machine Learning
https://simons.berkeley.edu/talks/aarti-singh-2017-5-5
1:03:24 Computational Challenges and the Future of ML Panel Panelists: Maryam Fazel (University of Washington), Yoav Freund (UC San Diego), Michael Jordan (UC Berkeley), Richard Karp (UC Berkeley), and Marina Meila (University of Washington).
Computational ...
42:41 The Polytope Learning Problem Navin Goyal, Microsoft Research
Computational Challenges in Machine Learning
https://simons.berkeley.edu/talks/navin-goyal-2017-5-4
42:11 System and Algorithm Co-Design, Theory and Practice, for Distributed Machine Learning Eric Xing, Carnegie Mellon University
Computational Challenges in Machine Learning
https://simons.berkeley.edu/talks/tba-4
52:08 Does Computational Complexity Restrict Artificial Intelligence (AI) and Machine Learning? Sanjeev Arora (Princeton University)
https://simons.berkeley.edu/events/openlectures2017-spring-4
Simons Institute Open Lecture
46:59 Computational Efficiency and Robust Statistics Ilias Diakonikolas, University of Southern California
Computational Challenges in Machine Learning
https://simons.berkeley.edu/talks/ilias-daikonikolas-2017...
35:35 Robust Estimation of Mean and Covariance Anup Rao, Georgia Institute of Technology
Computational Challenges in Machine Learning
https://simons.berkeley.edu/talks/anup-rao-2017-5-4
1:08:02 Embedding as a Tool for Algorithm Design Le Song, Georgia Institute of Technology
Computational Challenges in Machine Learning
https://simons.berkeley.edu/talks/le-song-2017-5-4
45:27 The Imitation Learning View of Structured Prediction Hal Daume, University of Maryland at College Park
Computational Challenges in Machine Learning
https://simons.berkeley.edu/talks/hal-daume-2017-5-3
29:39 Exponential Computational Improvement by Reduction John Langford, Microsoft Research New York
Computational Challenges in Machine Learning
https://simons.berkeley.edu/talks/john-langford-2017-5-3
50:12 Machine Learning Combinatorial Optimization Algorithms Dorit Hochbaum, UC Berkeley
Computational Challenges in Machine Learning
https://simons.berkeley.edu/talks/dorit-hochbaum-2017-5-3
40:49 A Cost Function for Similarity-Based Hierarchical Clustering Sanjoy Dasgupta, UC San Diego
Computational Challenges in Machine Learning
https://simons.berkeley.edu/talks/tba-3
1:09:46 Machine Learning for Healthcare Data Katherine Heller, Duke University
Computational Challenges in Machine Learning
https://simons.berkeley.edu/talks/katherine-heller-2017-5-3
45:18 Efficient Distributed Deep Learning Using MXNet Anima Anandkumar, UC Irvine
Computational Challenges in Machine Learning
https://simons.berkeley.edu/talks/anima-anandkumar-2017-5-5
39:37 Your Neural Network Can't Learn Mine John Wilmes, Georgia Institute of Technology
Computational Challenges in Machine Learning
https://simons.berkeley.edu/talks/tba-2
48:31 Sampling Polytopes: From Euclid to Riemann Yin Tat Lee, Microsoft Research and University of Washington
Computational Challenges in Machine Learning
https://simons.berkeley.edu/talks/yin-tat-lee-2017-5-2
38:54 Understanding Generalization in Adaptive Data Analysis Vitaly Feldman, IBM Almaden
Computational Challenges in Machine Learning
https://simons.berkeley.edu/talks/vitaly-feldman-2017-5-2
1:02:06 On Gradient-Based Optimization: Accelerated, Distributed, Asynchronous and Stochastic Michael Jordan, UC Berkeley
Computational Challenges in Machine Learninghttps://simons.berkeley.edu/talks/michael-jordan-2017-5-2
53:37 Stochastic Gradient MCMC for Independent and Dependent Data Sources Emily Fox, University of Washington
Computational Challenges in Machine Learning
https://simons.berkeley.edu/talks/emily-fox-2017-05-01
46:48 Scaling Up Bayesian Inference for Big and Complex Data David Dunson, Duke University
Computational Challenges in Machine Learning
https://simons.berkeley.edu/talks/david-dunson-2017-5-1
36:23 Unbiased Estimation of the Spectral Properties of Large Implicit Matrices Ryan Adams, Harvard University
Computational Challenges in Machine Learning
https://simons.berkeley.edu/talks/tba
44:41 Representational and Optimization Properties of Deep Residual Networks Peter Bartlett, UC Berkeley
Computational Challenges in Machine Learning
https://simons.berkeley.edu/talks/tba-1
41:36 Composing Graphical Models with Neural Networks for Structured Representations and Fast Inference David Duvenaud, University of Toronto
Computational Challenges in Machine Learning
https://simons.berkeley.edu/talks/david-duvenaud-2017-5-1
1:05:29 Variational Inference: Foundations and Innovations David Blei, Columbia University
Computational Challenges in Machine Learning
https://simons.berkeley.edu/talks/david-blei-2017-5-1