Description: Many current approaches in machine learning are heuristic: we cannot prove good bounds on either their performance or their running time. This small workshop will focus on the project of designing algorithms and approaches whose performance can be analyzed rigorously. The goal is to look beyond settings where provable bounds already exist.
Participation by invitation only; please send email to Ankur Moitra (moitra) if you wish to participate. We intend this to be a small meeting with active participation from all attendees – both speakers and non-speakers. Students who would like to attend the workshop should send a paragraph describing their researchinterests and background, and the relevance of this workshop to them. The deadline for registration is Thursday, July 26th.
Dates: The workshop will go from 10am on August 1 to 4pm on August 2 and will be held at the computer science dept, Princeton University.
Program/Schedule: (abstracts)
Wednesday, August 1st:
9:30-10:00 Breakfast and coffee (provided)
10:00-11:00 Michael Collins "Provable ML Methods for Natural Language Processing" [Video]
11:00-12:00 Sanjeev Arora. "Is Machine Learning Easy? Three Vignettes" [Video]
12:00-1:30 Lunch (provided)
1:30-2:30 Sham Kakade " Scalable Spectral Methods for Learning Latent Variable Models" [Video]
2:30-3:30 Percy Liang "Learning Latent-Variable Models of Natural Language" [Video]
3:30-4:00 Coffee break
4:00-5:00 David Sontag "Probabilistic Inference as Statistical Recovery" [Video]
5:00-6:00 Yann LeCun "Deep Learning: The Theoretician's Nightmare or Paradise?" [Video]
6:30-9 Dinner (provided) and informal discussion session
Thursday, August 2nd:
9:30-10:00 Breakfast and coffee (provided)
10:00-11:00 John Lafferty "Dictionary Learning and Sparsified Covariance Matrices for Linear Estimation" [Video]
11:00-12:00 Rob Schapire "Explaining Adaboost" [Video]
12:00-1:30 Lunch (provided)
1:30-2:30 Nina Balcan "Incorporating Unlabeled Data and Interaction in the Learning Process" [Video]
2:30-3:00 Coffee break
3:00-4:00 Sasha Rakhlin "Online Learning: A Minimax Analysis and an Algorithmic Framework" [Video]
Hotel: If you plan to come to the workshop and need a hotel room, we suggest that you reserve a room at the Nassau Inn as soon as possible. Their phone number is 1-800-862-7728. Please see the workshop announcement to see if there is a group code and an available group discount – such a rate will only be available if you book over the phone and not online!
Information for Speakers: We are covering the travel costs for all speakers. Travel costs for other participants should bearranged by the organizers (Sanjeev Arora arora and Moses Charikar moses). Speakers getting travel support are expected to use US flag carriers (NSF policy), but in exceptional cases we do have some unrestricted funds that can be used to pay for flights on non-US carriers. Once the workshop is over, you will have 30 days to submit your expense report as described here.
Important: If the travel includes stops in addition to the workshop location, appropriate documentation including the fare comparison direct to/from the conference location at the time of purchase must be included with the request for reimbursement. Documentation/comparisons cannot be dated after the trip dates. Question regarding fare comparisons can be directed to Mitra Kelly (mkelly).
Students: If we have funding available for students, there will be a support request form on the workshop announcement. Please follow the above guidelines (e.g. using a US carrier, submit reimbursement within 30 days).
Directions: We are located next to the Friend Center. The building has two parts, with computer science on the south side of the building. A university map of the building location is available here. A map of the general area is available here. There is a shuttle service you can reserve in advance called Olympic Airporter (ask for PU rate). A list of Princeton Taxis is available here. The Newark airport website should also have information regarding transportation. You can also click here for information for Princeton university visitors including driving directions and maps.
Parking: Visitors should park in Lot 21 in a visitor indicated spot and place this permit on the dashboard. The East Commuter Line shuttle service runs to/from the parking lot. See here for a schedule (search for “East Commuter Line”). There is also some metered street parking available on Olden and Prospect (bring about $10 in quarters).
Wireless Access: Use the network “csvapornet” (it is an open network).