Organizing Committee
Abstract

Recent advances in machine learning have had a profound impact on computer vision. Simultaneously, success in computer vision applications has rapidly increased our understanding of some machine learning techniques, especially their applicability. This workshop will bring together researchers who are building a stronger theoretical understanding of the foundations of machine learning with computer vision researchers who are advancing our understanding of machine learning in practice.

Much of the recent growth in the use of machine learning in computer vision has been spurred by advances in deep neural networks. At the same time, new advances in other areas of machine learning, including reinforcement learning, generative models, and optimization methods, hold great promise for future impact. These raise important fundamental questions, such as understanding what influences the ability of learning algorithms to generalize, understanding what causes optimization in learning to converge to effective solutions, and understanding how to make optimization more efficient.

The workshop will include machine learning researchers who are addressing these foundational questions. It will also include computer vision researchers who are applying machine learning to a host of problems, such as visual categorization, 3D reconstruction, event and activity understanding, and semantic segmentation.

Confirmed Speakers & Participants

  • Speaker
  • Poster Presenter
  • Attendee

Workshop Schedule

Monday, February 18, 2019
TimeEventLocationMaterials
8:30 - 8:55Registration - ICERM 121 South Main Street, Providence RI 0290311th Floor Collaborative Space 
8:55 - 9:00Welcome - ICERM Director11th Floor Lecture Hall 
9:00 - 9:45Learning spoken concepts from unlabeled audio-visual data - Karen Livescu, TTI-Chicago11th Floor Lecture Hall
10:00 - 10:30Coffee/Tea Break11th Floor Collaborative Space 
10:30 - 11:15Old-School Computer Vision Teaching Modern Deep Networks - Tal Hassner, The Open University of Israel11th Floor Lecture Hall
11:30 - 12:15Strong-Weak Adversarial Domain Adaptation - Kate Saenko, Boston University11th Floor Lecture Hall
12:30 - 2:30Break for Lunch / Free Time  
2:30 - 3:15Stochastic Video Generation with a Learned Prior - Rob Fergus, NYU & Facebook11th Floor Lecture Hall
3:30 - 4:00Coffee/Tea Break11th Floor Collaborative Space 
3:30 - 4:15Learning to Optimize Multigrid PDE Solvers - Ronen Basri, Weizmann Institute of Science 11th Floor Lecture Hall 
5:00 - 6:30Welcome Reception11th Floor Collaborative Space 
Tuesday, February 19, 2019
TimeEventLocationMaterials
9:00 - 9:45Analyzing Optimization in Deep Learning via Trajectories - Nadav Cohen, Institute for Advanced Study11th Floor Lecture Hall
10:00 - 10:30Coffee/Tea Break11th Floor Collaborative Space 
10:30 - 11:15Mathematics of Deep Learning - Rene Vidal, Johns Hopkins University11th Floor Lecture Hall
11:30 - 12:15Towards Joint Understanding of Images and Language - Svetlana Lazebnik, University of Illinois at Urbana-Champaign11th Floor Lecture Hall
12:30 - 2:30Break for Lunch / Free Time  
2:30 - 3:15Task2Vec- Task Embedding for Model Recommendation - Subhransu Maji, Umass Amherst11th Floor Lecture Hall
3:30 - 5:00Poster Session 11th Floor Collaborative Space 
Wednesday, February 20, 2019
TimeEventLocationMaterials
9:00 - 9:45Learning with Little Data - Richard Zemel, Vector Institute, Toronto11th Floor Lecture Hall 
10:00 - 10:30Coffee/Tea Break11th Floor Collaborative Space 
10:30 - 11:15Mad Max - Affine Spline Insights into Deep Learning - Richard Baraniuk, Rice University11th Floor Lecture Hall
11:30 - 12:15Accelerating atomic-scale calculations with machine learning - Andrew Peterson, School of Engineering, Brown University11th Floor Lecture Hall
12:30 - 12:40Group Photo11th Floor Lecture Hall 
12:40 - 2:30Break for Lunch / Free Time  
2:30 - 3:15A theoretical look at adversarial examples and dataset poisoning - Tom Goldstein, University of Maryland11th Floor Lecture Hall
3:30 - 4:00Coffee/Tea Break11th Floor Collaborative Space 
4:00 - 4:45Panel Discussion11th Floor Lecture Hall 
Thursday, February 21, 2019
TimeEventLocationMaterials
9:00 - 9:45The K-FAC method for neural network optimization - James Martens, DeepMind11th Floor Lecture Hall
10:00 - 10:30Coffee/Tea Break11th Floor Collaborative Space 
10:30 - 11:15Gradient descent aligns the layers of deep linear networks - Matus Telgarsky, University of Illinois Urbana-Champaign11th Floor Lecture Hall
11:30 - 12:15The Information Bottleneck theory of Deep Learning and the computational benefit of the hidden layers - Naftali Tishby, Hebrew University of Jerusalem11th Floor Lecture Hall
12:30 - 2:30Break for Lunch / Free Time  
2:30 - 3:15On The Power of Curriculum Learning in Training Deep Networks - Daphna Weinshall, Hebrew University of Jerusalem11th Floor Lecture Hall
3:30 - 4:00Coffee/Tea Break11th Floor Collaborative Space 
4:00 - 4:45Reconstructing Animals - David Jacobs, University of Maryland11th Floor Lecture Hall
Friday, February 22, 2019
TimeEventLocationMaterials
9:00 - 9:45Over-parameterized nonlinear learning - Gradient descent follows the shortest path - Mahdi Soltanolkotabi, University of Southern California11th Floor Lecture Hall
10:00 - 10:30Coffee/Tea Break11th Floor Collaborative Space 
10:30 - 11:15Learning Spatial Common Sense with Geometry-Aware Deep Networks - Katerina Fragkiadaki, Carnegie Mellon University11th Floor Lecture Hall
11:30 - 12:15Tensorial Neural Networks - Generalization of Neural Networks and Application to Model Compression - Furong Huang, University of Maryland11th Floor Lecture Hall
12:30 - 2:30Break for Lunch / Free Time  
3:30 - 4:00Coffee/Tea Break11th Floor Collaborative Space 

Request Reimbursement

Acceptable Costs
  • 1 roundtrip between your home institute and ICERM
  • Flights on U.S. or E.U. airlines – economy class to either Providence airport (PVD) or Boston airport (BOS)
  • Ground Transportation to and from airports and ICERM.
Unacceptable Costs
  • Flights on non-U.S. or non-E.U. airlines
  • Flights on U.K. airlines
  • Seats in economy plus, business class, or first class
  • Change ticket fees of any kind
  • Multi-use bus passes
  • Meals or incidentals
Advance Approval Required
  • Personal car travel to ICERM from outside New England
  • Multiple-destination plane ticket; does not include layovers to reach ICERM
  • Arriving or departing from ICERM more than a day before or day after the program
  • Multiple trips to ICERM
  • Rental car to/from ICERM
  • Flights on a Swiss, Japanese, or Australian airlines
  • Arriving or departing from airport other than PVD/BOS or home institution's local airport
  • 2 one-way plane tickets to create a roundtrip (often purchased from Expedia, Orbitz, etc.)
Reimbursement Request Form

https://icerm.brown.edu/money/

Refer to the back of your ID badge for more information. Checklists are available at the front desk.

Reimbursement Tips
  • Scanned original receipts are required for all expenses
  • Airfare receipt must show full itinerary and payment
  • ICERM does not offer per diem or meal reimbursement
  • Allowable mileage is reimbursed at prevailing IRS Business Rate and trip documented via pdf of Google Maps result
  • Keep all documentation until you receive your reimbursement!
Reimbursement Timing

6 - 8 weeks after all documentation is sent to ICERM. All reimbursement requests are reviewed by numerous central offices at Brown who may request additional documentation.

Reimbursement Deadline

Submissions must be received within 30 days of ICERM departure to avoid applicable taxes. Submissions after thirty days will incur applicable taxes. No submissions are accepted more than six months after the program end.

Associated Semester Workshops

Computer Vision
Algebraic Vision Research Cluster
Computational Imaging

Lecture Videos

Towards Joint Understanding of Images and Language

Svetlana Lazebnik
University of Illinois, Urbana-Champaign
February 19, 2019

Stochastic Video Generation with a Learned Prior

Rob Fergus
Courant Institute of Mathematical Sciences, New York University
February 18, 2019