Equivariant Frames and the Impossibility of Continuous Canonicalization

• URL: http://arxiv.org/abs/2402.16077v2
• Date: Tue, 18 Jun 2024 12:07:34 GMT
• Title: Equivariant Frames and the Impossibility of Continuous Canonicalization
• Authors: Nadav Dym, Hannah Lawrence, Jonathan W. Siegel,
• Abstract summary: We show that unweighted frame-averaging can turn a smooth, non-symmetric function into a discontinuous, symmetric function. We construct efficient and continuous weighted frames for the actions of $SO(2)$, $SO(3)$, and $S_n$ on point clouds.
• Score: 10.02508080274145
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Canonicalization provides an architecture-agnostic method for enforcing equivariance, with generalizations such as frame-averaging recently gaining prominence as a lightweight and flexible alternative to equivariant architectures. Recent works have found an empirical benefit to using probabilistic frames instead, which learn weighted distributions over group elements. In this work, we provide strong theoretical justification for this phenomenon: for commonly-used groups, there is no efficiently computable choice of frame that preserves continuity of the function being averaged. In other words, unweighted frame-averaging can turn a smooth, non-symmetric function into a discontinuous, symmetric function. To address this fundamental robustness problem, we formally define and construct \emph{weighted} frames, which provably preserve continuity, and demonstrate their utility by constructing efficient and continuous weighted frames for the actions of $SO(2)$, $SO(3)$, and $S_n$ on point clouds.

Related papers

• A Canonicalization Perspective on Invariant and Equivariant Learning [54.44572887716977]
  We introduce a canonicalization perspective that provides an essential and complete view of the design of frames. We show that there exists an inherent connection between frames and canonical forms. We design novel frames for eigenvectors that are strictly superior to existing methods.
  arXiv  Detail & Related papers  (2024-05-28T17:22:15Z)
• A Robustness Analysis of Blind Source Separation [91.3755431537592]
  Blind source separation (BSS) aims to recover an unobserved signal from its mixture $X=f(S)$ under the condition that the transformation $f$ is invertible but unknown. We present a general framework for analysing such violations and quantifying their impact on the blind recovery of $S$ from $X$. We show that a generic BSS-solution in response to general deviations from its defining structural assumptions can be profitably analysed in the form of explicit continuity guarantees.
  arXiv  Detail & Related papers  (2023-03-17T16:30:51Z)
• Equivariance with Learned Canonicalization Functions [77.32483958400282]
  We show that learning a small neural network to perform canonicalization is better than using predefineds. Our experiments show that learning the canonicalization function is competitive with existing techniques for learning equivariant functions across many tasks.
  arXiv  Detail & Related papers  (2022-11-11T21:58:15Z)
• Object Representations as Fixed Points: Training Iterative Refinement Algorithms with Implicit Differentiation [88.14365009076907]
  Iterative refinement is a useful paradigm for representation learning. We develop an implicit differentiation approach that improves the stability and tractability of training.
  arXiv  Detail & Related papers  (2022-07-02T10:00:35Z)
• Rockafellian Relaxation and Stochastic Optimization under Perturbations [0.056247917037481096]
  We develop an optimistic" framework based on Rockafellian relaxations in which optimization is conducted not only over the original decision space but also jointly with a choice of model. The framework centers on the novel concepts of exact and limit-exact Rockafellians, with interpretations of negative'' regularization emerging in certain settings.
  arXiv  Detail & Related papers  (2022-04-10T20:02:41Z)
• Tensor Completion with Provable Consistency and Fairness Guarantees for Recommender Systems [5.099537069575897]
  We introduce a new consistency-based approach for defining and solving nonnegative/positive matrix and tensor completion problems. We show that a single property/constraint: preserving unit-scale consistency, guarantees the existence of both a solution and, under relatively weak support assumptions, uniqueness.
  arXiv  Detail & Related papers  (2022-04-04T19:42:46Z)
• Frame Averaging for Invariant and Equivariant Network Design [50.87023773850824]
  We introduce Frame Averaging (FA), a framework for adapting known (backbone) architectures to become invariant or equivariant to new symmetry types. We show that FA-based models have maximal expressive power in a broad setting. We propose a new class of universal Graph Neural Networks (GNNs), universal Euclidean motion invariant point cloud networks, and Euclidean motion invariant Message Passing (MP) GNNs.
  arXiv  Detail & Related papers  (2021-10-07T11:05:23Z)
• A Unified Framework for Constructing Nonconvex Regularizations [0.0]
  How to construct non regularization function remains open in this paper. In this paper, we fill in the form of a non regularization function.
  arXiv  Detail & Related papers  (2021-06-11T02:10:01Z)
• On dissipative symplectic integration with applications to gradient-based optimization [77.34726150561087]
  We propose a geometric framework in which discretizations can be realized systematically. We show that a generalization of symplectic to nonconservative and in particular dissipative Hamiltonian systems is able to preserve rates of convergence up to a controlled error.
  arXiv  Detail & Related papers  (2020-04-15T00:36:49Z)
• Convergence to Second-Order Stationarity for Non-negative Matrix Factorization: Provably and Concurrently [18.89597524771988]
  Non-negative matrix factorization (NMF) is a fundamental non-modification optimization problem with numerous applications in Machine Learning. This paper defines a multiplicative weight update type dynamics (Seung algorithm) that runs concurrently and provably avoids saddle points. An important advantage is the use concurrent implementations in parallel computing environments.
  arXiv  Detail & Related papers  (2020-02-26T06:40:23Z)

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.