Workshops

Spring 2017

Interactive Learning

Feb 13, 2017 to Feb 17, 2017

Return to event »

Click on the titles of individual talks for abstract, slides and archived video (if applicable).

All events take place in the Calvin Lab Auditorium.

Monday, February 13th, 2017
9:00 am–9:20 am		Coffee and Check-In
9:20 am–9:30 am		Opening Remarks
9:30 am–10:15 am		Machine Learning from Verbal User Instruction Tom Mitchell, Carnegie Mellon University
10:15 am–10:45 am		Break
10:45 am–11:30 am		Machine Teaching in Interactive Learning Jerry Zhu, University of Wisconsin-Madison
11:30 am–1:30 pm		Lunch
1:30 pm–2:15 pm		Interactively Learning Robot Objective Functions Anca Dragan, UC Berkeley
2:15 pm–3:00 pm		Words, Pictures, and Common Sense Devi Parikh, Georgia Institute of Technology
3:00 pm–3:30 pm		Break
3:30 pm–4:15 pm		Stochastic Variance Reduction Methods for Policy Evaluation Lihong Li, Microsoft Research
4:15 pm–5:00 pm		Discussion
5:00 pm–6:00 pm		Reception

Tuesday, February 14th, 2017
9:00 am–9:30 am		Coffee and Check-In
9:30 am–10:15 am		Interactive Clustering Pranjal Awasthi, Rutgers University
10:15 am–10:45 am		Break
10:45 am–11:30 am		Crowdsourcing and Machine Learning Adam Kalai, Microsoft Research New England
11:30 am–1:30 pm		Lunch
1:30 pm–2:15 pm		Active Learning Beyond Label Feedback Kamalika Chaudhuri, UC San Diego
2:15 pm–3:00 pm		Active Learning for Multidimensional Experimental Spaces of Biological Responses Robert Murphy, Carnegie Mellon University
3:00 pm–3:30 pm		Break
3:30 pm–4:15 pm		Interactive Language Learning from the Extremes Sida Wang, Stanford University
4:15 pm–5:00 pm		Discussion

Wednesday, February 15th, 2017
9:00 am–9:30 am		Coffee and Check-In
9:30 am–10:15 am		Robot Learning from Motor-Impaired Teachers and Task Partners Brenna Argall, Northwestern University
10:15 am–10:45 am		Break
10:45 am–11:30 am		Sample-Efficient Reinforcement Learning with Rich Observations Alekh Agarwal, Microsoft Research New York
11:30 am–1:30 pm		Lunch
1:30 pm–2:15 pm		Robots Learning from Human Interactions Andrea Thomaz, University of Texas at Austin
2:15 pm–3:00 pm		Robot Learning, Interaction and Reliable Autonomy Sonia Chernova, Georgia Institute of Technology
3:00 pm–3:30 pm		Break
3:30 pm–4:15 pm		Interactive Learning of Parsers from Weak Supervision Luke Zettlemoyer, University of Washington
4:15 pm–5:00 pm		Discussion

Thursday, February 16th, 2017
9:00 am–9:30 am		Coffee and Check-In
9:30 am–10:15 am		Power of Active Sampling for Unsupervised Learning Aarti Singh, Carnegie Mellon University
10:15 am–10:45 am		Break
10:45 am–11:30 am		Leveraging Union of Subspace Structure to Improve Constrained Clustering L aura Balzano, University of Michigan
11:30 am–1:30 pm		Lunch
1:30 pm–1:45 pm		Corralling a Band of Bandit Algorithms Haipeng Luo, Microsoft Research
1:45 pm–2:00 pm		The End of Optimism? An Asymptotic Analysis of Finite-Armed Linear Bandits Csaba Szepesvari, University of Alberta
2:05 pm–2:20 pm		RL of Partially Observable Environments Using Spectral Methods Kamyar Azizzadenesheli, UC Irvine
2:20 pm–2:35 pm		Safety in Exploration Andreas Krause, ETH Zurich
2:40 pm–3:00 pm		Optimizing the Spec in RL Emma Brunskill, Carnegie Mellon University
3:00 pm–3:30 pm		Break
3:30 pm–3:45 pm		I-SED: An Interactive Sound Event Detector Bongjun Kim, Northwestern University
3:45 pm–4:00 pm		Data Dependent Hierarchical Interactive Classification Learning Shai Ben-David, Univeristy of Waterloo
4:05 pm–4:20 pm		Learning with Feature Feedback: From Theory to Practice Stefanos Poulis, UC San Diego
4:20 pm–4:35 pm		Active Nearest Neighbors in Changing Environments Ruth Urner, Max Planck Institute for Intelligent Systems, Tuebingen
4:40 pm–5:00 pm		Interactive Learning Opportunities for the Air Force Lee Seversky, Air Force Research Laboratory

Friday, February 17th, 2017
9:00 am–9:30 am		Coffee and Check-In
9:30 am–10:15 am		Hierarchical Learning for Human-Robot Collaboration Brian Scassellati, Yale University
10:15 am–11:00 am		Active Nearest-Neighbor Learning in Metric Spaces Sivan Sabato, Ben Gurion University
11:00 am–11:30 am		Break
11:30 am–12:30 pm		Systems Presentation Alekh Agarwal, Microsoft Research New York and Lalit Jain, University of Michigan
12:30 pm–2:00 pm		Lunch
2:00 pm–2:45 pm		TicToc: A General Technique for Near-Optimal Active Learning with Noise Steve Hanneke
2:45 pm–3:30 pm		Interactive Learning of Mixtures of Submodular Functions Jeff Bilmes, University of Washington