Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

24487296 · Jun 202019922001200920172026
48 results for universal equivariance

Universal MLPs with a single hidden layer can learn any function.

problem Learning on various data structures like sequences, images, sets, and graphs.
method Using group theory, the paper proves the universality of a broad class of equivariant MLPs with a single hidden layer.
result Having a hidden layer on which the group acts regularly is sufficient for universal equivariance (invariance).

Using deep neural networks that are either invariant or equivariant to permutations in order to learn functions on unordered sets has become prevalent. The most popular, basic models are DeepSets [Zaheer et al. 2017] and PointNet [Qi et al. 2017]. While known to be universal for approximating invariant functions, DeepS…

2019-10-06abs ↗pdf ↗

Unified method for CNNs to approximate equivariant maps across various groups.

problem Limited universal approximation theorems for CNNs with specific groups and settings.
method Unified approach to derive universal approximation theorems for equivariant maps by CNNs in diverse settings.
result Ability to handle non-linear equivariant maps between infinite-dimensional spaces for non-compact groups.

This work establishes universality for deep equivariant networks, overcoming limitations of previous approaches.

problem Rarity of universality results for equivariant neural networks, especially in high-dimensional settings.
method Develops a more general account of universality for equivariant networks, introducing entry-wise separability and readout layers.
result Deep equivariant networks achieve universality under entry-wise separability, with or without readout layers.

Study shows limitations and universality of equivariant QNNs with SnS_n-equivariant gates.

problem Understanding the expressiveness of SnS_n-equivariant QNNs with kk-body gates.
method Investigated the interplay between symmetry and kk-bodyness in SnS_n-equivariant QNN generators.
result QNNs are semi-universal but not universal with one- and two-body SnS_n-equivariant gates.

We give a classifying theory for LGLG-bundles, where LGLG is the loop group of a compact Lie group GG, and present a calculation for the string class of the universal LGLG-bundle. We show that this class is in fact an equivariant cohomology class and give an equivariant differential form representing it. We then use t…

2010-05-24abs ↗pdf ↗

Global group laws connect equivariant bordism rings to formal group laws.

problem Establishing connections between equivariant bordism rings and formal group laws.
method Global homotopy theory framework; proving isomorphisms and universal properties.
result Equivariant bordism rings are isomorphic to Lazard rings for abelian Lie groups.

New method uses scalars to approximate physics functions.

problem Designing neural networks that respect physical symmetries.
method Parameterizing polynomial functions equivariant to various symmetries using scalars.
result Universal approximation of polynomial functions under various symmetries using scalars.

A universal collection of 4 invariants improves neural network accuracy for molecular dynamics.

problem Improving accuracy of neural networks in molecular dynamics.
method Developed a universal collection of 4 smooth scalar invariants on M(3) x M(3) and evaluated their effectiveness in a PONITA neural network architecture.
result Using a universal collection of invariants significantly improves neural network accuracy.

The Euler characteristic is the only additive topological invariant for spaces of certain sort, in particular, for manifolds with some finiteness properties. A generalization of the notion of a manifold is the notion of a V-manifold. Here we discuss a universal additive topological invariant of V-manifolds: the univers…

2018-04-23abs ↗pdf ↗

Graph Neural Networks (GNN) come in many flavors, but should always be either invariant (permutation of the nodes of the input graph does not affect the output) or equivariant (permutation of the input permutes the output). In this paper, we consider a specific class of invariant and equivariant networks, for which we …

2019-05-13abs ↗pdf ↗

Transformers can approximate any sequence-to-sequence function, surprising given their complexity.

problem Understanding the expressive power of Transformer models for sequence-to-sequence functions.
method Established that Transformers are universal approximators of continuous permutation equivariant sequence-to-sequence functions with compact support, and extended this to arbitrary functions using positional encodings.
result Transformers are universal approximators of arbitrary continuous sequence-to-sequence functions on a compact domain.

The paper generalizes equivariant neural networks on homogeneous spaces to the non-linear setting.

problem Equivariant neural networks on homogeneous spaces.
method Deriving generalized steerability constraints for non-linear equivariant layers.
result The universality of the derived construction for non-linear equivariant layers.

A classical theorem due to Quillen (1969) identifies the unitary bordism ring with the Lazard ring, which classifies the universal one-dimensional commutative formal group law. We prove an equivariant generalization of this result by identifying the homotopy theoretic Z/2\mathbb{Z}/2-equivariant unitary bordism ring, in…

2017-11-07abs ↗pdf ↗

GNP models predictive correlations and outperforms NPs.

problem Training and understanding of Neural Processes.
method Proposed a new model, Gaussian Neural Process (GNP), which incorporates translation equivariance and provides universal approximation guarantees.
result Demonstrates encouraging performance and provides universal approximation guarantees.

Frame Averaging makes neural networks invariant or equivariant to new symmetries.

problem Designing neural networks that respect symmetries while being expressive and efficient.
method Introduces Frame Averaging (FA) as a systematic framework to adapt architectures to become invariant or equivariant to new symmetries.
result Frame Averaging guarantees exact invariance or equivariance while being simpler to compute than full group averaging.

For every positive integer nn we construct a bigraded homology theory for links, such that the corresponding invariant of the unknot is closely related to the U(n)-equivariant cohomology ring of CPn1\mathbb{CP}^{n-1}; our construction specializes to the Khovanov-Rozansky slnsl_n-homology. We are motivated by the "univers…

2008-04-23abs ↗pdf ↗

The paper studies moduli spaces of non-smooth metric structures with non-negative Ricci curvature.

problem Understanding moduli spaces of non-smooth metric structures with non-negative Ricci curvature.
method Relating convergence of RCD(0,N)-structures to their lifts, constructing Albanese and soul maps, proving their continuity, and constructing examples.
result Construction of moduli spaces with non-trivial rational homotopy groups.

The objective of this paper is to clarify the relationships between the quantum D-module and equivariant Floer theory. Equivariant Floer theory was introduced by Givental in his paper ``Homological Geometry''. He conjectured that the quantum D-module of a symplectic manifold is isomorphic to the equivariant Floer cohom…

2004-10-22abs ↗pdf ↗

An impossibility result shows limitations in learning symmetries and equivariant functions.

problem Learning symmetries and equivariant functions simultaneously is impossible under certain conditions.
method Careful study of approximation for groups and semigroups, analysis of neural networks.
result Linearly equivariant networks can be used to learn equivariant functions, but group-convolutional networks have limitations.

We present effective methods to compute equivariant harmonic maps from the universal cover of a surface into a nonpositively curved space. By discretizing the theory appropriately, we show that the energy functional is strongly convex and derive convergence of the discrete heat flow to the energy minimizer, with explic…

2018-10-29abs ↗pdf ↗

Constructs equivariant spectral flow for Dirac-type operators on manifolds.

problem Calculating spectral flow for Dirac-type operators on manifolds with group actions.
method Equivariant spectral flow construction for paths of Dirac-type operators on manifolds.
result Relates delocalised η-invariants and ρ-invariants for different positive scalar curvature metrics.

New graph foundation models respect symmetries for broader applicability.

problem Tailored graph machine learning architectures limit broader applicability.
method Investigates symmetries for label and feature permutations, proving network universal approximator.
result Universal approximator on multisets respecting node and feature permutations.

TACE unifies scalar and tensorial modeling in Cartesian space for accurate, stable, and efficient atomistic predictions.

problem Complexity and challenges in equivariant atomistic machine learning models.
method Tensor Atomic Cluster Expansion (TACE) in Cartesian space, decomposing local environments into irreducible Cartesian tensors (ICT).
result Universal invariant and equivariant embeddings, enabling explicit control at inference.

Let G be a connected Lie group with Lie algebra g. The Duflo map is a vector space isomorphism between the symmetric algebra S(g) and the universal enveloping algebra U(g) which, as proved by Duflo, restricts to a ring isomorphism from invariant polynomials onto the center of the universal enveloping algebra. The Duflo…

1999-03-09abs ↗pdf ↗

Link homology compared with geometric link invariants using Bott-Samelson varieties.

problem Comparing different link homology theories with geometric link invariants.
method Using Khovanov-Rozansky homology and equivariant cohomology applied to Bott-Samelson varieties.
result Equivariant integral sl(n) link homology with specialized or universal potential.

New fusion blocks improve equivariant neural networks for molecular dynamics.

problem Designing equivariant neural networks for tasks with global symmetries.
method Using fusion diagrams from tensor networks to design novel equivariant components.
result Improved performance with fewer parameters on chemical problems.

Novel CG-EGNNs learn equivariant functions from Clifford algebras.

problem Lack of equivariance in high-order graph neural networks.
method Integrates high-order local structures with Clifford algebras for equivariant learning.
result CG-EGNNs outperform previous methods on various benchmarks.

The paper develops tensor learning methods exploiting symmetries of tensor functions.

problem Efficiently handling tensors in various scientific contexts.
method Equivariant machine learning architectures exploiting orthogonal, Lorentz, and symplectic symmetries.
result Equivariant models outperform non-equivariant baselines in time series analysis.

GemNet improves molecular predictions by overcoming graph neural network limitations.

problem Graph neural networks struggle with distinguishing certain types of molecular graphs.
method Discretized geometric message passing neural network (GemNet) with spherical representations.
result GemNet outperforms previous models on molecular datasets by 34-20%.

The paper characterizes equivariant immersions in hyperbolic space.

problem Characterizing equivariant immersions in hyperbolic space.
method Analyzes the Gauss map of equivariant immersions in hyperbolic space.
result Provides two characterizations of equivariant immersions: one in terms of the Maslov class and another for compact MM in terms of Hamiltonian symplectomorphisms.

The theory of principal GG-bundles over a Lie groupoid is an important one, unifying the various types of principal GG-bundles, including those over manifolds, those over orbifolds, as well as equivariant principal GG-bundles. In this paper, we study the differential geometry of these objects, including connections …

2004-01-29abs ↗pdf ↗

Paper introduces Deep Sets for Symmetric Elements (DSS) layers for learning sets of symmetric elements.

problem Learning sets of symmetric elements is underexplored.
method Characterized equivariant layers, showed DSS layers are universal approximators, and demonstrated their effectiveness.
result DSS layers improve set-learning architectures across various data types.