Timezone: »

Deep Learning through Information Geometry
Pratik Chaudhari · Alexander Alemi · Varun Jog · Dhagash Mehta · Frank Nielsen · Stefano Soatto · Greg Ver Steeg

Sat Dec 12 09:20 AM -- 06:30 PM (PST) @
Event URL: https://sites.google.com/view/dl-info-neurips20 »

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: [ protected link dropped ]

Author Information

Pratik Chaudhari (University of Pennsylvania)
Alexander 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