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.

168,694 papers · 148 categories

Trend · papers per month

102205307409 · Jun 202019922001200920172026
48 results for equivariant bounding

The study examines how equivariance in networks affects generalization error using PAC-Bayesian bounds.

problem Understanding how equivariance in networks impacts generalization error.
method Utilized PAC-Bayesian analysis for equivariant networks, deriving norm-based bounds for generalization error.
result The bound indicates that using larger group size in the model improves generalization error.

Study improves generalization bounds for equivariant networks on Markov data.

problem Challenges in integrating equivariance with Markov dependencies in neural networks.
method Applied McDiarmid's inequality and computed covering number using group theory.
result Derived upper bound on Rademacher complexity for equivariant neural networks on Markov datasets.

Study on equivariant Heegaard genus of reducible 3-manifolds with group actions.

problem Understanding the equivariant Heegaard genus of reducible 3-manifolds with group actions.
method Thin position theory for 3-dimensional orbifolds to establish bounds on equivariant Heegaard genus.
result Sharp bounds on equivariant Heegaard genus of reducible manifolds, similar to tunnel number results.

Group invariant and equivariant Multilayer Perceptrons (MLP), also known as Equivariant Networks, have achieved remarkable success in learning on a variety of data structures, such as sequences, images, sets, and graphs. Using tools from group theory, this paper proves the universality of a broad class of equivariant M…

2020-02-07abs ↗pdf ↗

The paper provides bounds for embedding manifolds into Euclidean spaces with group actions.

problem Finding explicit bounds for embedding manifolds into Euclidean spaces with group actions.
method The paper provides upper and lower bounds for the dimension of the Euclidean space required for equivariant embeddings of manifolds into Euclidean spaces for finite group actions.
result Explicit bounds for the dimension of the Euclidean space required for equivariant embeddings of manifolds into Euclidean spaces for finite group actions.

We will provide a lower bound for the equivariant Lusternik-Schnirelmann category of an arbitrary proper action in terms of the stratification by orbit types, and an upper bound for proper polar actions in terms of the equivariant Lusternik-Schnirelmann category of its generalized Weyl group. As an application we repro…

2007-04-26abs ↗pdf ↗

Defines a new homomorphism for strongly invertible knots, proving equivariant algebraic concordance.

problem Equivariant algebraic concordance of strongly invertible knots.
method Defining a homomorphism ΦΦ from equivariant concordance group to a new equivariant algebraic concordance group, proving it lifts known homomorphisms and provides new obstructions.
result Obtains a new obstruction to equivariant sliceness and novel lower bounds on equivariant slice genus.

This work introduces a method for almost equivariance in neural networks using Lie algebra convolutions.

problem Real-world data often does not conform to strict group equivariances, leading to underperformance in models.
method Definition and practical implementation of almost equivariance through Lie algebra convolutions.
result Demonstrated the validity of the approach through benchmarking against fully equivariant settings.

Study on knots, genera, and algebraic concordance groups.

problem Understanding the equivariant slice genus of strongly invertible knots.
method Using the Blanchfield form to establish lower bounds and formulate an equivariant algebraic concordance group.
result The equivariant slice genus of an equivariant connected sum of a genus one strongly invertible slice knot is at least n/4.

The study examines how weight sharing, equivariance, and locality affect the sample complexity of neural networks.

problem Understanding the impact of design choices on the generalization error of neural networks.
method Statistical learning theory applied to single hidden layer networks with weight sharing, equivariance, and locality.
result Lower and upper bounds for sample complexity are derived, showing that locality has benefits but comes with a trade-off.

We show that the S^1-equivariant Yamabe invariant of the 3-sphere, endowed with the Hopf action, is equal to the (non-equivariant) Yamabe invariant of the 3-sphere. More generally, we establish a topological upper bound for the S^1-equivariant Yamabe invariant of any closed oriented 3-manifold endowed with an S^1-actio…

2015-08-11abs ↗pdf ↗

SymPE breaks symmetries in equivariant networks, improving performance across various tasks.

problem Equivariant networks cannot break symmetries, leading to poor performance in tasks with symmetrical inputs.
method Novel equivariant conditional distributions and randomized canonicalization.
result SymPE significantly improves performance of group-equivariant and graph neural networks.

Let M2nM^{2n} be a unitary torus (2n)(2n)-manifold, i.e., a (2n)(2n)-dimensional oriented stable complex connected closed TnT^n-manifold having a nonempty fixed set. In this paper we show that MM bounds equivariantly if and only if the equivariant Chern numbers <(c1Tn)i(c2Tn)j,[M]>=0< (c_1^{T^n})^i(c_2^{T^n})^j, [M]>=0 for all $i, j\in {\Bbb …

2011-03-31abs ↗pdf ↗

The study proves a generic multiplicity one theorem for GG-invariant minimal hypersurfaces.

problem Proving a generic multiplicity one theorem for GG-invariant minimal hypersurfaces.
method Equivariant min-max theory and analysis of GG-homology classes.
result Shows a generic multiplicity one theorem for GG-invariant minimal hypersurfaces.

This paper explores how enforcing equivariance constraints limits neural network expressivity and proposes compensatory model size increases.

problem The impact of enforcing equivariance constraints on the expressive power of neural networks.
method Examined 2-layer ReLU networks, analyzed boundary hyperplanes and channel vectors, and constructed upper bounds on model size required for compensation.
result Enforcing equivariance constraints reduces the expressive power of neural networks, but this can be compensated by increasing model size.

The paper defines and calculates an upper bound for the equivariant crossing number of two-bridge knots.

problem Finding the minimum number of crossings in symmetric diagrams for two-bridge knots.
method Defining and calculating c2(K)c_2(K) for two-bridge knots by restricting diagrams to two types.
result An algorithm to determine c2(K)c_2(K) for any two-bridge knot and results up to 14 crossings.

The paper finds a special hypersurface in a manifold with positive Ricci curvature.

problem Finding a special hypersurface in a manifold with positive Ricci curvature.
method Equivariant min-max method applied to GG-manifolds.
result The hypersurface is a multiplicity one minimal GG-hypersurface.

The paper investigates how symmetry in models affects their performance and generalization.

problem Understanding how symmetry in models impacts their performance and generalization.
method Formal unified investigation of intuitions about symmetry in models and data.
result Quantitative bounds and comparisons between model and data equivariance lead to optimal model performance.

Our work improves VAE latent space clustering by enforcing invariant and equivariant learning.

problem Current VAEs fail to learn invariant and equivariant clusters in latent space.
method We use a mixture model pdf like Gaussian mixtures to enforce deep, group-invariant learning and separate semantic and equivariant variables.
result Our model effectively learns to disentangle invariant and equivariant representations, improving learning rate and image recognition.

We show a non-existence result for some class of equivariant maps between sphere bundles over tori. The notion of equivariant KO-degree is used in the proof. As an application to Seiberg-Witten theory, for a connected closed oriented spin 4-manifold with indefinite intersection form, we have a new bound of the second B…

2005-02-24abs ↗pdf ↗

Let a compact Lie group act isometrically on a non-collapsing sequence of compact Alexandrov spaces with fixed dimension and uniform lower curvature and upper diameter bounds. If the sequence of actions is equicontinuous and converges in the equivariant Gromov--Hausdorff topology, then the limit space is equivariantly …

2014-01-02abs ↗pdf ↗

Let GG a semisimple Lie group of non-compact type and let XG\mathcal{X}_G be the Riemannian symmetric space associated to it. Suppose XG\mathcal{X}_G has dimension nn and it has no factor isometric to either H2\mathbb{H}^2 or SL(3,R)/SO(3)\text{SL}(3,\mathbb{R})/\text{SO}(3). Given a closed nn-dimensional Riemannian manifold $…

2019-11-13abs ↗pdf ↗

New Wasserstein divergence improves generative model robustness and structure preservation.

problem Improving generative model robustness and structure preservation.
method Introduces a novel Wasserstein-1 path-space divergence and a WUP theorem.
result Derives robustness and generalization bounds for flow-based models.

Study proves obstructions to equivariantly slice strongly negative amphichiral knots.

problem Proving obstructions for equivariantly slice strongly negative amphichiral knots.
method Using determinant, Spinc-structures, Donaldson's theorem, and Heegaard Floer correction terms.
result 8 out of 16 strongly negative amphichiral knots with 12 or fewer crossings are not equivariantly slice.

The paper calculates the equivariant genus for a specific type of knot.

problem Calculating the equivariant genus of marked strongly invertible knots associated with 2-bridge knots.
method Analyzing invariant Seifert surfaces for marked strongly invertible knots.
result The paper completely determines the equivariant genus for every marked strongly invertible knot with KK a 2-bridge knot.