Timezone: »
Attempts at understanding deep learning have come from different disciplines, namely physics, statistics, information theory, and machine learning. These lines of investigation have very different modeling assumptions and techniques; it is unclear how their results may be reconciled together. This workshop builds upon the observation that Information Geometry has strong overlaps with these directions and may serve as a means to develop a holistic understanding of deep learning. The workshop program is designed to answer two specific questions. The first question is: how do geometry of the hypothesis class and information-theoretic properties of optimization inform generalization. Good datasets have been a key propeller of the empirical success of deep networks. Our theoretical understanding of data is however poor. The second question the workshop will focus on is: how can we model data and use the understanding of data to improve optimization/generalization in the low-data regime.
Gather.Town link: https://neurips.gather.town/app/vPYEDmTHeUbkACgf/dl-info-neurips2020
|
Sat 9:20 a.m. - 9:30 a.m.
|
Opening Remarks
|
|
|
Sat 9:30 a.m. - 10:15 a.m.
|
Keynote 1: Ke Sun
(Keynote)
Video
|
Ke Sun |
|
Sat 10:15 a.m. - 10:30 a.m.
|
Contributed Talk 1: The Volume of Non-Restricted Boltzmann Machines and Their Double Descent Model Complexity
(Contributed Talk)
»
Video
Prasad Cheema, Mahito Sugiyama |
Prasad Cheema, Mahito Sugiyama |
|
Sat 10:30 a.m. - 10:45 a.m.
|
Contributed Talk 2: From em-Projections to Variational Auto-Encoder
(Contributed Talk)
»
Video
Tian Han, Jun Zhang, Ying Nian Wu |
Tian Han |
|
Sat 10:45 a.m. - 11:30 a.m.
|
Keynote 2: Marco Gori
(Keynote)
Video
|
Marco Gori |
|
Sat 12:30 p.m. - 1:15 p.m.
|
Keynote 3: Shun-ichi Amari
(Keynote)
Video
|
Shun-ichi Amari |
|
Sat 1:15 p.m. - 2:00 p.m.
|
Keynote 4: Alexander Rakhlin
(Keynote)
|
Alexander Rakhlin |
|
Sat 2:15 p.m. - 2:30 p.m.
|
Contributed Talk 3: An Information-Geometric Distance on the Space of Tasks
(Contributed Talk)
»
Video
Yansong Gao, Pratik Chaudhari |
Yansong Gao |
|
Sat 2:30 p.m. - 3:15 p.m.
|
Keynote 5: Gintare Karolina Dziugaite
(Keynote)
Video
|
Gintare Karolina Dziugaite |
|
Sat 3:15 p.m. - 4:00 p.m.
|
Keynote 6: Guido Montufar
(Keynote)
|
Guido Montufar |
|
Sat 4:00 p.m. - 4:15 p.m.
|
Contributed Talk 4: Annealed Importance Sampling with q-Paths
(Contributed Talk)
»
Video
Rob Brekelmans, Vaden Masrani, Thang D Bui, Frank Wood, Aram Galstyan, Greg Ver Steeg, Frank Nielsen |
Rob Brekelmans |
|
Sat 4:30 p.m. - 5:00 p.m.
|
Panel Discussion and Closing Remarks
|
|
|
Sat 5:00 p.m. - 6:30 p.m.
|
Poster Session (Gather Town) (Poster Session) |
Author Information
Pratik Chaudhari (University of Pennsylvania)
Alex Alemi (Google)
Varun Jog (University of Wisconsin-Madison)
Dhagash Mehta (The Vanguard Group)
Frank Nielsen (Sony CS Labs Inc.)
Stefano Soatto (UCLA)
Greg Ver Steeg (USC Information Sciences Institute)
More from the Same Authors
-
2020 Poster: Predicting Training Time Without Training »
Luca Zancato · Alessandro Achille · Avinash Ravichandran · Rahul Bhotika · Stefano Soatto -
2020 Poster: Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction »
Tong He · John Collomosse · Hailin Jin · Stefano Soatto -
2020 Poster: Fast, Accurate, and Simple Models for Tabular Data via Augmented Distillation »
Rasool Fakoor · Jonas Mueller · Nick Erickson · Pratik Chaudhari · Alexander Smola -
2020 Poster: Targeted Adversarial Perturbations for Monocular Depth Prediction »
Alex Wong · Safa Cicek · Stefano Soatto -
2019 Poster: Time Matters in Regularizing Deep Networks: Weight Decay and Data Augmentation Affect Early Learning Dynamics, Matter Little Near Convergence »
Aditya Sharad Golatkar · Alessandro Achille · Stefano Soatto -
2019 Poster: Fast structure learning with modular regularization »
Greg Ver Steeg · Hrayr Harutyunyan · Daniel Moyer · Aram Galstyan -
2019 Spotlight: Fast structure learning with modular regularization »
Greg Ver Steeg · Hrayr Harutyunyan · Daniel Moyer · Aram Galstyan -
2019 Poster: Exact Rate-Distortion in Autoencoders via Echo Noise »
Rob Brekelmans · Daniel Moyer · Aram Galstyan · Greg Ver Steeg -
2018 Poster: Invariant Representations without Adversarial Training »
Daniel Moyer · Shuyang Gao · Rob Brekelmans · Aram Galstyan · Greg Ver Steeg -
2018 Poster: Watch Your Step: Learning Node Embeddings via Graph Attention »
Sami Abu-El-Haija · Bryan Perozzi · Rami Al-Rfou · Alexander Alemi -
2018 Poster: GILBO: One Metric to Measure Them All »
Alexander Alemi · Ian Fischer -
2018 Spotlight: GILBO: One Metric to Measure Them All »
Alexander Alemi · Ian Fischer -
2016 Poster: DeepMath - Deep Sequence Models for Premise Selection »
Geoffrey Irving · Christian Szegedy · Alexander Alemi · Niklas Een · Francois Chollet · Josef Urban -
2016 Poster: Variational Information Maximization for Feature Selection »
Shuyang Gao · Greg Ver Steeg · Aram Galstyan -
2016 Poster: Computing and maximizing influence in linear threshold and triggering models »
Justin Khim · Varun Jog · Po-Ling Loh -
2014 Poster: Discovering Structure in High-Dimensional Data Through Correlation Explanation »
Greg Ver Steeg · Aram Galstyan -
2012 Poster: Controlled Recognition Bounds for Visual Learning and Exploration »
Vasiliy Karasev · Alessandro Chiuso · Stefano Soatto -
2011 Poster: Multiple Instance Filtering »
Kamil A Wnuk · Stefano Soatto
