Timezone: »

Object Representations as Fixed Points: Training Iterative Refinement Algorithms with Implicit Differentiation
Michael Chang · Tom Griffiths · Sergey Levine

Tue Nov 29 02:00 PM -- 04:00 PM (PST) @ Hall J #505

Current work in object-centric learning has been motivated by developing learning algorithms that infer independent and symmetric entities from the perceptual input. This often requires the use iterative refinement procedures that break symmetries among equally plausible explanations for the data, but most prior works differentiate through the unrolled refinement process, which can make optimization exceptionally challenging. In this work, we observe that such iterative refinement methods can be made differentiable by means of the implicit function theorem, and develop an implicit differentiation approach that improves the stability and tractability of training such models by decoupling the forward and backward passes. This connection enables us to apply recent advances in optimizing implicit layers to not only improve the stability and optimization of the slot attention module in SLATE, a state-of-the-art method for learning entity representations, but do so with constant space and time complexity in backpropagation and only one additional line of code.

Author Information

Michael Chang (University of California, Berkeley)

Ph.D. student at Berkeley AI Research, U.C. Berkeley B.S. in Computer Science from MIT Former research intern under Juergen Schmidhuber, Istituto Dalle Molle di Studi sull'Intelligenza Artificiale (IDSIA) Former undergraduate researcher under Joshua Tenenbaum and Antonio Torralba, MIT

Tom Griffiths (Princeton University)
Sergey Levine (UC Berkeley)

More from the Same Authors