NIPS 2017

A list of slides of all talks from NIPS 2017

This year’s Neural Information Processing Systems (NIPS) 2017 conference held at Long Beach Convention Center, Long Beach California has been the biggest ever! Here’s a list of resources and slides of all invited talks, tutorials and workshops.

NIPS 2017

This list is still incomplete and will be regularly updated. Contributions are welcome. You can add links via pull requests or create an issue in the Github Repo to lemme know something I missed or to start a discussion. If you know the speakers, please ask them to upload slides online!

Invited Talks

• Powering the next 100 years, John Platt
• Why AI Will Make it Possible to Reprogram the Human Genome, Brendan J Frey
• The Trouble with Bias, Kate Crawford
• The Unreasonable Effectiveness of Structure, John Platt
• Deep Learning for Robotics, Pieter Abbeel
• Learning State Representations, Yael Niv
• On Bayesian Deep Learning and Deep Bayesian Learning, Yee Whye Teh

Tutorials

• Deep Learning: Practice and Trends, Nando de Freitas · Scott Reed · Oriol Vinyals
• Reinforcement Learning with People, Emma Brunskill
• A Primer on Optimal Transport, Marco Cuturi · Justin M Solomon
• Deep Probabilistic Modelling with Gaussian Processes, Neil D Lawrence
• Fairness in Machine Learning, Solon Barocas · Moritz Hardt
• Statistical Relational Artificial Intelligence: Logic, Probability and Computation, Luc De Raedt · David Poole · Kristian Kersting · Sriraam Natarajan
• Engineering and Reverse-Engineering Intelligence Using Probabilistic Programs, Program Induction, and Deep Learning, Josh Tenenbaum · Vikash K Mansinghka
• Differentially Private Machine Learning: Theory, Algorithms and Applications, Kamalika Chaudhuri · Anand D Sarwate
• Geometric Deep Learning on Graphs and Manifolds, Michael Bronstein · Joan Bruna · Arthur Szlam · Xavier Bresson · Yann LeCun

Workshops

ML Systems Workshop @ NIPS 2017

Aparna Lakshmiratan · Sarah Bird · Siddhartha Sen · Christopher Ré · Li Erran Li · Joseph Gonzalez · Daniel Crankshaw

• A distributed execution engine for emerging AI applications, Ion Stoica
• The Case for Learning Database Indexes
• Federated Multi-Task Learning, Virginia Smith
• Accelerating Persistent Neural Networks at Datacenter Scale, Daniel Lo
• DLVM: A modern compiler framework for neural network DSLs, Richard Wei · Lane Schwartz · Vikram Adve
• Machine Learning for Systems and Systems for Machine Learning, Jeff Dean
• Creating an Open and Flexible ecosystem for AI models with ONNX, Sarah Bird · Dmytro Dzhulgakov
• NSML: A Machine Learning Platform That Enables You to Focus on Your Models, Nako Sung
• DAWNBench: An End-to-End Deep Learning Benchmark and Competition, Cody Coleman

Bayesian Deep Learning

Yarin Gal · José Miguel Hernández-Lobato · Christos Louizos · Andrew G Wilson · Diederik P. (Durk) Kingma · Zoubin Ghahramani · Kevin P Murphy · Max Welling

• Why Aren’t You Using Probabilistic Programming?, Dustin Tran
• Automatic Model Selection in BNNs with Horseshoe Priors, Finale Doshi
• Deep Bayes for Distributed Learning, Uncertainty Quantification and Compression, Max Welling
• Stochastic Gradient Descent as Approximate Bayesian Inference, Matt Hoffman
• Recent Advances in Autoregressive Generative Models, Nal Kalchbrenner
• Deep Kernel Learning, Russ Salakhutdinov
• Bayes by Backprop, Meire Fortunato
• How do the Deep Learning layers converge to the Information Bottleneck limit by Stochastic Gradient Descent?, Naftali (Tali) Tishby

Learning with Limited Labeled Data: Weak Supervision and Beyond

Isabelle Augenstein · Stephen Bach · Eugene Belilovsky · Matthew Blaschko · Christoph Lampert · Edouard Oyallon · Emmanouil Antonios Platanios · Alexander Ratner · Christopher Ré

• Welcome Note
• Tales from fMRI: Learning from limited labeled data, Gaël Varoquaux
• Learning from Limited Labeled Data (But a Lot of Unlabeled Data), Tom Mitchell
• Light Supervision of Structured Prediction Energy Networks, Andrew McCallum
• Forcing Neural Link Predictors to Play by the Rules, Sebastian Riedel
• Panel: Limited Labeled Data in Medical Imaging, Daniel Rubin · Matt Lungren · Ina Fiterau
• Sample and Computationally Efficient Active Learning Algorithms, Nina Balcan
• That Doesn’t Make Sense! A Case Study in Actively Annotating Model Explanations, Sameer Singh
• Overcoming Limited Data with GANs, Ian Goodfellow
• What’s so Hard About Natural Language Understanding?, Alan Ritter
• Closing Remarks

Advances in Approximate Bayesian Inference

Francisco Ruiz · Stephan Mandt · Cheng Zhang · James McInerney · Dustin Tran · Tamara Broderick · Michalis Titsias · David Blei · Max Welling

• Learning priors, likelihoods, or posteriors, Iain Murray
• Learning Implicit Generative Models Using Differentiable Graph Tests, Josip Djolonga
• Gradient Estimators for Implicit Models, Yingzhen Li
• Variational Autoencoders for Recommendation, Dawen Liang
• Approximate Inference in Industry: Two Applications at Amazon, Cedric Archambeau
• Variational Inference based on Robust Divergences, Futoshi Futami
• Adversarial Sequential Monte Carlo, Kira Kempinska
• Scalable Logit Gaussian Process Classification, Florian Wenzel
• Variational inference in deep Gaussian processes, Andreas Damianou
• Taylor Residual Estimators via Automatic Differentiation, Andrew Miller
• Differential privacy and Bayesian learning, Antti Honkela
• Frequentist Consistency of Variational Bayes, Yixin Wang

Symposiums

Interpretable Machine Learning

Andrew G Wilson · Jason Yosinski · Patrice Simard · Rich Caruana · William Herlands

• The role of causality for interpretability, Bernhard Scholkopf , Slides · Video
• Interpretable Discovery in Large Image Data Sets, Kiri Wagstaff, Slides · Video
• The (hidden) Cost of Calibration, Bernhard Scholkopf, Slides · Video
• Panel Discussion, Hanna Wallach, Kiri Wagstaff, Suchi Saria, Bolei Zhou, and Zack Lipton. Moderated by Rich Caruana, Video
• Interpretability for AI safety, Victoria Krakovna, Slides · Video
• Manipulating and Measuring Model Interpretability, Jenn Wortman Vaughan, Slides · Video
• Debugging the Machine Learning Pipeline, Jerry Zhu, Slides · Video
• Panel Debate and Followup Discussion, Yann LeCun, Kilian Weinberger, Patrice Simard, and Rich Caruana, Video

Deep Reinforcement Learning

Pieter Abbeel · Yan Duan · David Silver · Satinder Singh · Junhyuk Oh · Rein Houthooft

• Mastering Games with Deep Reinforcement Learning, David Silver, Video
• Reproducibility in Deep Reinforcement Learning and Beyond, Joelle Pineau, Slides · Video
• Neural Map: Structured Memory for Deep RL, Ruslan Salakhutdinov, Slides
• Deep Exploration Via Randomized Value Functions, Ben Van Roy, Slides · Video
• Artificial Intelligence Goes All-In, Michael Bowling

WiML

• Bayesian machine learning: Quantifying uncertainty and robustness at scale, Tamara​ ​Broderick​
• Towards Communication-Centric Multi-Agent Deep Reinforcement Learning for Guarding a Territory, Aishwarya​ ​Unnikrishnan
• Graph convolutional networks can encode three-dimensional genome architecture in deep learning models for genomics, Peyton​ ​Greenside​
• Machine Learning for Social Science, Hannah​ ​Wallach​
• Fairness Aware Recommendations, Palak​ ​Agarwal​
• Reinforcement Learning with a Corrupted Reward Channel, Victoria​ ​Krakivna​
• Improving health-care: challenges and opportunities for reinforcement learning, Joelle​ ​Pineau​
• Harnessing Adversarial Attacks on Deep Reinforement Learning for Improving Robustness, Zhenyi​ ​Tang​
• Time-Critical Machine Learning, Nina​ ​Mishra​
• A General Framework for Evaluating Callout Mechanisms in Repeated Auctions, Hoda​ ​Heidari​
• Engaging Experts: A Dirichlet Process Approach to Divergent Elicited Priors in Social Science, Sarah​ ​Bouchat​
• Representation Learning in Large Attributed Graphs, Nesreen​ ​K​ ​Ahmed​

If you like what you are reading, follow Deep Hunt — a weekly AI newsletter with special focus on Machine Learning to stay updated in this fast moving field. You can also follow or tweet at me on Twitter!