9.00 - 10.00 Morning session I
9.00 - 9.05 Opening Remarks
9.05 - 9.45 Invited Talk - Alekh Agarwal - Corralling a band of bandit algorithms
9.45 - 10.05 Contributed talk by Xinkun Nie - Why adaptively collected data has negative bias and how to correct for it.
10.05 - 10.25 Morning coffee break
10.25 - 12.00 Morning session
10.25 - 10:45 Invited talk - Travis Dick - Label Efficient Learning by Exploiting Multi-class Output Codes.
10:45 - 11.05 Tutorial - Giulia DeSalvo - Learning with Rejection
11:05 - 11:25 Contributed Talk by Nidhi Hegde - Active Learning in Expert Systems Experiments on StackExchange Data.
11.25 - 11.45 Contributed Talk by Marc Pickett - A Brief Study of In-Domain Transfer and Learning from Fewer Samples using A Few Simple Priors.
11.45 - 12.05 Contributed Talk by Mandana Hamidi-Haines - Active Multi-Label Learning with Varying Query Sets.
12.05 - 14.00 Lunch break
14.00 - 15.00 Afternoon session I
14.00 - 14.40 Panel discussion:
Panelists:
Panelist 1: Alekh Agarwal
Panelist 2: Michal Valko
Panelist 3: Mehryar Mohri
14.40 - 15.00 Contributed talk by Saket Maheshwary - Data Driven Feature Learning.
15.00 - 15.30 Afternoon coffee break
15.30 - 17.35 Afternoon session II
15.30 - 16.10 Invited talk - Michal Valko - Faster graph bandit learning using information about the neighbors
16.10 - 16.30 Contributed talk by Keerthiram Murugesan - Active Learning from Peers.
16.30 - 17.10 Invited talk - Claudio Gentile - On leveraging structure in nonstochastic bandit problems: some examples
17.10 - 17.30 Invited Student talk - Liran Szlak - Online Learning with Local Permutations and Delayed Feedback
17.30 - 17.35 Wrap-up