The conference on Neural Information Processing Systems (NeurIPS) is held in Vancouver this year. Professionals and academics gather together at this event to present and learn the latest research over the course of tutorials, main conference sessions and workshops.
SigOpt is excited to return to NeurIPS as a Platinum Sponsor and to continue supporting this community. Below is a list of activities that we are hosting or participating in. Feel free to join us for any of these activities throughout the week. If you can’t make it to the events, search for us on the Whova app and we are happy to find a time to connect. We look forward to seeing you at these events!
UPDATE: NeurIPS is over, and what a meeting it was. Read our review for more info.
Meet SigOpt at NeurIPS
Expo Demonstration: Advanced Hyperparameter Optimization Methods
Sunday, December 8 – 9:00am-6:00pm
We will provide a prescriptive guide for hyperparameter optimization (HPO) that includes techniques for using HPO throughout the modeling process and real-world examples of the impact of this approach.
In particular, this demo will include ways to apply advanced HPO methods to address:
- Metric definition, selection and optimization
- Data and feature transformation parameter tuning
- Architecture tuning as part of hyperparameter optimization
- Deep learning model convergence with automated early stopping
- Long training cycles with multitask tuning and parallelism
For each of these use cases, the team will share more detail around the research underpinning for these HPO techniques as well as an applied use case that contextualizes how to incorporate it into the modeling process. The goal is for this combination to offer useful information for modelers, modeling team leaders and modeling platform engineers.
Visit us all week at Booth #323
Have questions or interested in learning more about SigOpt? Visit us at booth #323 in the exhibit hall to meet our team. We are happy to talk about our academic program, the exciting career opportunities at SigOpt, or learn about your modeling work and share how SigOpt can help accelerate your modeling process. Schedule a 1:1 with our team for a time to connect. And, as always, pick up some SigOpt SWAG along the way!
Workshop Papers
Applying Bayesian Optimization to Understand Tradeoffs for Antireflective Optical Designs [blog]
Sajad Haghanifar, Michael McCourt, Bolong Cheng, Paul Leu
Workshop: Second Workshop on Machine Learning and the Physical Sciences
Saturday, December 14th, 8:00 AM — 6:00 PM @ West Meeting Rooms 109 & 110
Automated Model Search Using Bayesian Optimization and Genetic Programming [pdf]
Louis Schlessinger, Gustavo Malkomes, Roman Garnett
Workshop: Workshop on Meta-Learning
Friday, December 13th, 8:00 AM — 6:00 PM @ West Ballroom B
Accelerating Psychometric Screening Tests With Bayesian Active Differential Selection [pdf]
Trevor Larsen, Gustavo Malkomes, Dennis Barbour
Workshop: ML4H: Machine Learning for Health
Friday, December 13th, 8:00 AM — 6:00 PM @ West Ballroom A
Parallel Robust Bayesian Optimization with Off-Policy Evaluations [pdf]
Javier Garcia-Barcos, Ruben Martinez-Cantin
Workshop: Safety and Robustness in Decision Making
Friday, December 13th, 8:00 AM — 6:00 PM @ East Ballroom A
Featured Articles
We are fortunate to be part of an active research community, including the work of experts in machine learning, statistics, operations research, mathematics, and numerous applications. We would like to highlight the work of current and former collaborators below and congratulate them on their achievements. Be sure to check out their talks, posters, blogs, and papers.
Certifying Geometric Robustness of Neural Networks [pdf]
Mislav Balunović, Maximilian Baader, Gagandeep Singh, Timon Gehr, Martin Vechev
Poster: Thursday, December 12th, 10:45 AM — 12:45 PM @ East Exhibition Hall B + C #13
Practical Two-Step Lookahead Bayesian Optimization [pdf]
Jian Wu, Peter Frazier
Poster: Thursday, December 12th, 10:45 AM — 12:45 PM @ East Exhibition Hall B + C #33
Meta-Surrogate Benchmarking for Hyperparameter Optimization [pdf]
Aaron Klein, Zhenwen Dai, Frank Hutter, Neil Lawrence, Javier Gonzalez
Poster: Tuesday, December 10th, 5:30 PM — 7:30 PM @ East Exhibition Hall B + C #6
D-VAE: A Variational Autoencoder for Directed Acyclic Graphs [pdf][slides]
Muhan Zhang, Shali Jiang, Zhicheng Cui, Roman Garnett, Yixin Chen
Poster: Tuesday, December 10th, 5:30 PM — 7:30 PM @ East Exhibition Hall B + C #1
Cost Effective Active Search [pdf][slides]
Shali Jiang, Roman Garnett, Benjamin Moseley
Poster: Thursday, December 12th, 10:45 AM — 12:45 PM @ East Exhibition Hall B + C #3
Scalable Global Optimization via Local Bayesian Optimization [pdf][slides]
David Eriksson, Michael Pearce, Jacob Gardner, Ryan Turner, Matthias Poloczek
Poster: Tuesday, December 10th, 5:30 PM — 7:30 PM @ East Exhibition Hall B + C #9
Efficiently Escaping Saddle Points on Manifolds [pdf][poster]
Christopher Criscitiello, Nicolas Boumal
Poster: Tuesday, December 10th, 5:30 PM — 7:30 PM @ East Exhibition Hall B + C #118
Large Scale Markov Decision Processes with Changing Rewards [pdf][slides]
Adrian Rivera Cardoso, He Wang, Huan Xu
Poster: Wednesday, December 11th, 5:00 PM — 7:00 PM @ East Exhibition Hall B + C #52