MLconf NYC 2017 Speaker Resources

Aaron Roth, Associate Professor, University of Pennsylvania

The Algorithmic Foundations of Differential Privacy

The Reusable Holdout: Preserving Validity in Adaptive Data Analysis

Alexandra Johnson, Software Engineer, SigOpt

Intro

Ian Dewancker. SigOpt for ML: TensorFlow ConvNets on a Budget with Bayesian Optimization

Ian Dewancker. SigOpt for ML: Unsupervised Learning with Even Less Supervision Using Bayesian Optimization

Ian Dewancker. SigOpt for ML: Bayesian Optimization for Collaborative Filtering with MLlib   

#1 Trusting the Defaults

Keras recurrent layers documentation

#2 Using the Wrong Metric

Ron Kohavi et al. Trustworthy Online Controlled Experiments: Five Puzzling Outcomes Explained

Xavier Amatriain. 10 Lessons Learning from Building ML Systems (Video at 19:03)  

Image from PhD Comics.

See also: SigOpt in Depth: Intro to Multicriteria Optimization

#4 Too Few Hyperparameters

Image from TensorFlow Playground

Ian Dewancker. SigOpt for ML: Unsupervised Learning with Even Less Supervision Using Bayesian Optimization

#5 Hand Tuning

On algorithms beating experts: Scott Clark, Ian Dewancker and Sathish Nagappan. Deep Neural Network Optimization with SigOpt and Nervana Cloud

#6 Grid Search

Nogridsearch.com

#7 Random Search

James Bergstra and Yoshua Bengio. Random Search for Hyper-parameter Optimization

Ian Dewancker, Michael McCourt, Scott Clark, Patrick Hayes, Alexandra Johnson, George Ke. A Stratified Analysis of Bayesian Optimization Methods

Learn More

Blog.sigopt.com

sigopt.com/research

Byron Galbraith, Chief Data Scientist, Talla

https://github.com/bgalbraith/bandits

Corinna Cortes, Head of Research, Google

https://arxiv.org/pdf/1611.00068.pdf

http://www.kdd.org/kdd2016/papers/files/Paper_1069.pdf

Erik Bernhardsson, CTO, Better Mortgage

https://github.com/spotify/annoy

https://github.com/erikbern/ann-benchmarks

https://github.com/erikbern/ann-presentation

https://erikbern.com/

 

Layla El Asri, Research Scientist, Maluuba
Improving Scalability of Reinforcement Learning by Separation of Concerns
Towards Information-Seeking Agents
Frames: A Corpus For Adding Memory To Goal-Oriented Dialogue Systems