Timezone: »

Real World Experiment Design and Active Learning
Ilija Bogunovic · Willie Neiswanger · Yisong Yue

Sat Jul 18 07:00 AM -- 03:35 PM (PDT) @ None
Event URL: https://realworldml.github.io/ »

This workshop aims to bring together researchers from academia and industry to discuss major challenges, outline recent advances, and highlight future directions pertaining to novel and existing large-scale real-world experiment design and active learning problems. We aim to highlight new and emerging research opportunities for the machine learning community that arise from the evolving needs to make experiment design and active learning procedures that are theoretically and practically relevant for realistic applications.

The intended audience and participants include everyone whose research interests, activities, and applications involve experiment design, active learning, bandit/Bayesian optimization, efficient exploration, and parameter search methods and techniques. We expect the workshop to attract substantial interest from researchers working in both academia and industry. The research of our invited speakers spans both theory and applications, and represents a diverse range of domains where experiment design and active learning are of fundamental importance (including robotics & control, biology, physical sciences, crowdsourcing, citizen science, etc.).

The schedule is with respect to UTC (i.e., Universal Time) time zone.

Sat 7:00 a.m. - 7:10 a.m.
Opening Statements (Discussion Panel)
Sat 7:15 a.m. - 7:50 a.m.
"Latent Space Optimization with Deep Generative Models" (Invited Talk)   
Jose Miguel Hernandez-Lobato
Sat 7:50 a.m. - 7:55 a.m.
Q&A ((w/ Jose M.H. Lobato))
Sat 8:00 a.m. - 8:35 a.m.
"Designing Bayesian-Optimal Experiments with Stochastic Gradients" (Invited Talk)   
Tom Rainforth
Sat 8:35 a.m. - 8:40 a.m.
Q&A ((w/ Tom Rainforth))
Sat 8:45 a.m. - 9:20 a.m.
"Active Learning of Robot Reward Functions" (Invited Talk)   
Dorsa Sadigh
Sat 9:20 a.m. - 9:25 a.m.
Q&A ((w/ Dorsa Sadigh))
Sat 9:30 a.m. - 10:05 a.m.
"Active Learning through Physically-embodied, Synthesized-from-“scratch” Queries" (Invited Talk)   
Anca Dragan
Sat 10:05 a.m. - 10:10 a.m.
Q&A ((w/ Anca Dragan))
Sat 10:15 a.m. - 11:40 a.m.
Lightning Talks and Discussion
Sat 11:45 a.m. - 12:25 p.m.
"Uncertainty Quantification Using Martingales for Misspecified Gaussian Processes" (Invited Talk)   
Aaditya Ramdas
Sat 12:25 p.m. - 12:30 p.m.
Q&A ((w/ Aaditya Ramdas))
Sat 12:35 p.m. - 1:10 p.m.
"Learning to Manage Inventory" (Invited Talk)   
Shipra Agrawal
Sat 1:10 p.m. - 1:15 p.m.
Q&A ((w/ Shipra Agrawal))
Sat 1:20 p.m. - 1:55 p.m.
"Machine learning-based design (of proteins, small molecules and beyond)" (Invited Talk)
Jennifer Listgarten
Sat 1:55 p.m. - 2:00 p.m.
Q&A ((w/ Jennifer Listgarten))
Sat 2:05 p.m. - 2:40 p.m.
"Safe and Efficient Active Learning Strategies for Robotics Applications" (Invited Talk)
Angela Schoellig
Sat 2:40 p.m. - 2:45 p.m.
Q&A ((w/ Angela Schoellig))
Sat 2:50 p.m. - 3:25 p.m.
"Towards Causal Benchmarking of Bias in Face Analysis Algorithm" (Invited Talk)
Pietro Perona
Sat 3:25 p.m. - 3:30 p.m.
Q&A ((w/ Pietro Perona))
Sat 3:30 p.m. - 3:35 p.m.
Closing Remarks (Discussion Panel)

Author Information

Ilija Bogunovic (ETH Zurich)
Willie Neiswanger (Carnegie Mellon University)
Yisong Yue (Caltech)

Yisong Yue is an assistant professor in the Computing and Mathematical Sciences Department at the California Institute of Technology. He was previously a research scientist at Disney Research. Before that, he was a postdoctoral researcher in the Machine Learning Department and the iLab at Carnegie Mellon University. He received a Ph.D. from Cornell University and a B.S. from the University of Illinois at Urbana-Champaign. Yisong's research interests lie primarily in the theory and application of statistical machine learning. He is particularly interested in developing novel methods for interactive machine learning and structured prediction. In the past, his research has been applied to information retrieval, recommender systems, text classification, learning from rich user interfaces, analyzing implicit human feedback, data-driven animation, behavior analysis, sports analytics, policy learning in robotics, and adaptive planning & allocation problems.

More from the Same Authors