Object Representations as Fixed Points: Training Iterative Refinement Algorithms with Implicit Differentiation

• URL: http://arxiv.org/abs/2207.00787v1
• Date: Sat, 2 Jul 2022 10:00:35 GMT
• Title: Object Representations as Fixed Points: Training Iterative Refinement Algorithms with Implicit Differentiation
• Authors: Michael Chang, Thomas L. Griffiths, Sergey Levine
• Abstract summary: Iterative refinement is a useful paradigm for representation learning. We develop an implicit differentiation approach that improves the stability and tractability of training.
• Score: 88.14365009076907
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Iterative refinement -- start with a random guess, then iteratively improve the guess -- is a useful paradigm for representation learning because it offers a way to break symmetries among equally plausible explanations for the data. This property enables the application of such methods to infer representations of sets of entities, such as objects in physical scenes, structurally resembling clustering algorithms in latent space. However, most prior works differentiate through the unrolled refinement process, which can make optimization challenging. We observe that such 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 by decoupling the forward and backward passes. This connection enables us to apply advances in optimizing implicit layers to not only improve the 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.

Related papers

• Efficient Fairness-Performance Pareto Front Computation [51.558848491038916]
  We show that optimal fair representations possess several useful structural properties. We then show that these approxing problems can be solved efficiently via concave programming methods.
  arXiv  Detail & Related papers  (2024-09-26T08:46:48Z)
• Semantics-Aware Dynamic Localization and Refinement for Referring Image Segmentation [102.25240608024063]
  Referring image segments an image from a language expression. We develop an algorithm that shifts from being localization-centric to segmentation-language. Compared to its counterparts, our method is more versatile yet effective.
  arXiv  Detail & Related papers  (2023-03-11T08:42:40Z)
• Linearization Algorithms for Fully Composite Optimization [61.20539085730636]
  This paper studies first-order algorithms for solving fully composite optimization problems convex compact sets. We leverage the structure of the objective by handling differentiable and non-differentiable separately, linearizing only the smooth parts.
  arXiv  Detail & Related papers  (2023-02-24T18:41:48Z)
• Backpropagation of Unrolled Solvers with Folded Optimization [55.04219793298687]
  The integration of constrained optimization models as components in deep networks has led to promising advances on many specialized learning tasks. One typical strategy is algorithm unrolling, which relies on automatic differentiation through the operations of an iterative solver. This paper provides theoretical insights into the backward pass of unrolled optimization, leading to a system for generating efficiently solvable analytical models of backpropagation.
  arXiv  Detail & Related papers  (2023-01-28T01:50:42Z)
• Differentiable Spline Approximations [48.10988598845873]
  Differentiable programming has significantly enhanced the scope of machine learning. Standard differentiable programming methods (such as autodiff) typically require that the machine learning models be differentiable. We show that leveraging this redesigned Jacobian in the form of a differentiable "layer" in predictive models leads to improved performance in diverse applications.
  arXiv  Detail & Related papers  (2021-10-04T16:04:46Z)
• Randomized Block-Diagonal Preconditioning for Parallel Learning [0.0]
  We study preconditioned gradient-based optimization methods where the preconditioning matrix has block-diagonal form. Our main contribution is to demonstrate that the convergence of these methods can significantly be improved by a randomization technique.
  arXiv  Detail & Related papers  (2020-06-24T10:12:36Z)
• MetaSDF: Meta-learning Signed Distance Functions [85.81290552559817]
  Generalizing across shapes with neural implicit representations amounts to learning priors over the respective function space. We formalize learning of a shape space as a meta-learning problem and leverage gradient-based meta-learning algorithms to solve this task.
  arXiv  Detail & Related papers  (2020-06-17T05:14:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.