EWRL and NIPS 2016

EWRL and NIPS 2016 I went to the European Workshop on Reinforcement Learning and NIPS last month and saw several interesting things. At EWRL, I particularly liked the talks from: Remi Munos on off-policy evaluation Mohammad Ghavamzadeh on learning safe policies Emma Brunskill on optimizing biased-but safe estimators (sense a theme?) Sergey Levine on low sample complexity applications of RL in robotics. My talk is here. Overall, this was a well organized workshop with diverse and interesting subjects, with the only caveat being that they had to limit registration At NIPS itself, I found the poster sessions fairly interesting. Allen-Zhu and Hazan had a new notion of a reduction (video). Zhao, Poupart, and Gordon had a new way to learn Sum-Product Networks Ho, Littman, MacGlashan, Cushman, and Austerwell, had a paper on how “Showing” is different from “Doing”. Toulis and…
Original Post: EWRL and NIPS 2016

Vowpal Wabbit version 8.3 and tutorial

Vowpal Wabbit version 8.3 and tutorial I just released Vowpal Wabbit 8.3 and we are planning a tutorial at NIPS Saturday over the lunch break in the ML systems workshop. Please join us if interested. 8.3 should be backwards compatible with all 8.x series. There have been big changes since the last version related to Contextual bandits, particularly w.r.t. the decision service. Learning to search for which we have a paper at NIPS. Logarithmic time multiclass classification.
Original Post: Vowpal Wabbit version 8.3 and tutorial

ICML 2016 videos and statistics

ICML 2016 videos and statistics The ICML 2016 videos are out. I also wanted to share some statistics from registration that might be of general interest. The total number of people attending: 3103. Industry: 47% University: 46% Male: 83% Female: 14% Local (NY, NJ, or CT): 27% North America: 70% Europe: 18% Asia: 9% Middle East: 2% Remainder: <1% including…
Original Post: ICML 2016 videos and statistics

The Multiworld Testing Decision Service

The Multiworld Testing Decision Service We made a tool that you can use. It is the first general purpose reinforcement-based learning system Reinforcement learning is much discussed these days with successes like AlphaGo. Wouldn’t it be great if Reinforcement Learning algorithms could easily be used to solve all reinforcement learning problems? But there is a well-known problem: It’s very easy…
Original Post: The Multiworld Testing Decision Service

An ICML unworkshop

An ICML unworkshop Following up on an interesting suggestion, we are creating a “Birds of a Feather Unworkshop” with a leftover room (Duffy/Columbia) on Thursday and Friday during the workshops. People interested in ad-hoc topics can post a time and place to meet and discuss. Details are here a little ways down.
Original Post: An ICML unworkshop

The ICML 2016 Space Fight

The space problem started long ago. At ICML last year and the year before the amount of capacity that needed to fit everyone on any single day was about 1500. My advice was to expect 2000 and have capacity for 2500 because “New York” and “Machine Learning”. Was history right? Or New York and buzz? I was not involved in…
Original Post: The ICML 2016 Space Fight

Room Sharing for ICML (and COLT, and ACL, and IJCAI)

Room Sharing for ICML (and COLT, and ACL, and IJCAI) My greatest concern with the many machine learning conferences in New York this year was the relatively high cost that implied, particularly for hotel rooms in Manhattan. Keeping the conference affordable for graduate students seems critical to what ICML is really about. The price becomes much more reasonable if you…
Original Post: Room Sharing for ICML (and COLT, and ACL, and IJCAI)

ICML registration is live

ICML registration is live Here. I would recommend registering early because there is a difficult to estimate(*) chance you will not be able to register later. The program is shaping up and should be of interest. The 9 Tutorials(**), 4 Invited Speakers, and 23 Workshops are all chosen, with paper decisions due out in a couple weeks. Early Full (after…
Original Post: ICML registration is live

AlphaGo is not the solution to AI

AlphaGo is not the solution to AI Congratulations are in order for the folks at Google Deepmind who have mastered Go. However, some of the discussion around this seems like giddy overstatement. Wired says Machines have conquered the last games and Slashdot says We know now that we don’t need any big new breakthroughs to get to true AI. The…
Original Post: AlphaGo is not the solution to AI