Global optimality under amenable symmetry constraints

• URL: http://arxiv.org/abs/2402.07613v2
• Date: Fri, 19 Jul 2024 08:50:31 GMT
• Title: Global optimality under amenable symmetry constraints
• Authors: Peter Orbanz,
• Abstract summary: We show the interplay between convexity, the group, and the underlying vector space, which is typically infinite-dimensional. We apply this toolkit to the invariant optimality problem. It yields new results on invariant kernel mean embeddings and risk-optimal invariant couplings.
• Score: 0.5656581242851759
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Consider a convex function that is invariant under an group of transformations. If it has a minimizer, does it also have an invariant minimizer? Variants of this problem appear in nonparametric statistics and in a number of adjacent fields. The answer depends on the choice of function, and on what one may loosely call the geometry of the problem -- the interplay between convexity, the group, and the underlying vector space, which is typically infinite-dimensional. We observe that this geometry is completely encoded in the smallest closed convex invariant subsets of the space, and proceed to study these sets, for groups that are amenable but not necessarily compact. We then apply this toolkit to the invariant optimality problem. It yields new results on invariant kernel mean embeddings and risk-optimal invariant couplings, and clarifies relations between seemingly distinct ideas, such as the summation trick used in machine learning to construct equivariant neural networks and the classic Hunt-Stein theorem of statistics.

Related papers

• Riemannian stochastic optimization methods avoid strict saddle points [68.80251170757647]
  We show that policies under study avoid strict saddle points / submanifolds with probability 1. This result provides an important sanity check as it shows that, almost always, the limit state of an algorithm can only be a local minimizer.
  arXiv  Detail & Related papers  (2023-11-04T11:12:24Z)
• Geometry of Linear Neural Networks: Equivariance and Invariance under Permutation Groups [0.0]
  We investigate the subvariety of functions that are equivariant or invariant under the action of a permutation group. We draw conclusions for the parameterization and the design of equivariant and invariant linear networks.
  arXiv  Detail & Related papers  (2023-09-24T19:40:15Z)
• The Exact Sample Complexity Gain from Invariances for Kernel Regression [37.74032673086741]
  In practice, encoding invariances into models improves sample complexity. We provide minimax optimal rates for kernel ridge regression on compact manifold. Our results hold for any smooth compact Lie group action, even groups of positive dimension.
  arXiv  Detail & Related papers  (2023-03-24T20:47:31Z)
• Multi-block-Single-probe Variance Reduced Estimator for Coupled Compositional Optimization [49.58290066287418]
  We propose a novel method named Multi-block-probe Variance Reduced (MSVR) to alleviate the complexity of compositional problems. Our results improve upon prior ones in several aspects, including the order of sample complexities and dependence on strongity.
  arXiv  Detail & Related papers  (2022-07-18T12:03:26Z)
• Linear programming with unitary-equivariant constraints [2.0305676256390934]
  Unitary equivariance is a natural symmetry that occurs in many contexts in physics and mathematics. We show that under additional symmetry assumptions, this problem reduces to a linear program that can be solved in time that does not scale in $d$. We also outline a possible route for extending our method to general unitary-equivariant semidefinite programs.
  arXiv  Detail & Related papers  (2022-07-12T17:37:04Z)
• Low Dimensional Invariant Embeddings for Universal Geometric Learning [6.405957390409045]
  This paper studies separating invariants: mappings on $D$ dimensional domains which are invariant to an appropriate group action, and which separate orbits. The motivation for this study comes from the usefulness of separating invariants in proving universality of equivariant neural network architectures.
  arXiv  Detail & Related papers  (2022-05-05T22:56:19Z)
• The Schr\"odinger Bridge between Gaussian Measures has a Closed Form [101.79851806388699]
  We focus on the dynamic formulation of OT, also known as the Schr"odinger bridge (SB) problem. In this paper, we provide closed-form expressions for SBs between Gaussian measures.
  arXiv  Detail & Related papers  (2022-02-11T15:59:01Z)
• Lattice-Based Methods Surpass Sum-of-Squares in Clustering [98.46302040220395]
  Clustering is a fundamental primitive in unsupervised learning. Recent work has established lower bounds against the class of low-degree methods. We show that, perhaps surprisingly, this particular clustering model textitdoes not exhibit a statistical-to-computational gap.
  arXiv  Detail & Related papers  (2021-12-07T18:50:17Z)
• On the Sample Complexity of Learning with Geometric Stability [42.813141600050166]
  We study the sample complexity of learning problems where the target function presents such invariance and stability properties. We provide non-parametric rates of convergence for kernel methods, and improvements in sample complexity by a factor equal to the size of the group.
  arXiv  Detail & Related papers  (2021-06-14T03:51:16Z)
• Coordinate Independent Convolutional Networks -- Isometry and Gauge Equivariant Convolutions on Riemannian Manifolds [70.32518963244466]
  A major complication in comparison to flat spaces is that it is unclear in which alignment a convolution kernel should be applied on a manifold. We argue that the particular choice of coordinatization should not affect a network's inference -- it should be coordinate independent. A simultaneous demand for coordinate independence and weight sharing is shown to result in a requirement on the network to be equivariant.
  arXiv  Detail & Related papers  (2021-06-10T19:54:19Z)
• Hybrid Trilinear and Bilinear Programming for Aligning Partially Overlapping Point Sets [85.71360365315128]
  In many applications, we need algorithms which can align partially overlapping point sets are invariant to the corresponding corresponding RPM algorithm. We first show that the objective is a cubic bound function. We then utilize the convex envelopes of trilinear and bilinear monomial transformations to derive its lower bound. We next develop a branch-and-bound (BnB) algorithm which only branches over the transformation variables and runs efficiently.
  arXiv  Detail & Related papers  (2021-01-19T04:24:23Z)

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.