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.

169,181 papers · 148 categories

Trend · papers per month

57114170227 · May 202619922001200920182026
48 results for Geometric Augmentation

Enhances deep networks with manifold exploration for better performance and robustness.

problem Improving deep neural network performance and robustness to random transformations.
method Geometric transformations learned through line-search manifold exploration to misclassify images while maintaining manifold consistency.
result Significantly increased robustness and performance on challenging classification tasks.

New findings on hyperbolicity of augmented links in thickened surfaces.

problem Proving hyperbolicity of links in thickened surfaces.
method Extending hyperbolicity results to generalized augmented cellular alternating links.
result Generalized augmented cellular alternating links in thickened surfaces are hyperbolic.

Generalizes fully augmented links to doubled 3-manifolds with geometric bounds.

problem Understanding the geometry of fully augmented links in doubled 3-manifolds.
method Constructing fully augmented links on the reflection surface of doubled 3-manifolds and finding bounds on cusp shapes and volumes.
result Bounds on cusp shapes and volumes of hyperbolic links in doubled 3-manifolds.

Study fully augmented links in thickened torus, generalizing S3S^3 results.

problem Classify and describe geometric properties of fully augmented links in thickened torus.
method Geometric analysis and decomposition of link complements into ideal right-angled torihedra.
result Proves Volume Density Conjecture for fully augmented links in thickened torus.

Adversarial learning improves image augmentation for neural networks.

problem Improving data augmentation for neural networks with limited data.
method Adversarial learning using an encoder-decoder architecture with a spatial transformer network.
result Our approach outperforms previous generative data augmentation methods.

This work characterizes how data augmentation shapes neural representations.

problem Understanding the impact of data augmentation on neural network representations.
method Embedding neural network hidden representations into a metric space invariant to transformations, analyzing shape-space trajectories.
result Increasing data augmentation strength leads to well-behaved trajectories in the embedded space, and different augmentation types steer representations in distinct directions.

Paper develops an unbiased risk estimator for learning with augmented classes.

problem Learning with augmented classes where unseen classes might appear in testing.
method Uses unlabeled training data to approximate potential distribution of augmented classes.
result Establishes an unbiased risk estimator for the testing distribution under mild assumptions.

Normal-bundle bootstrap generates new data preserving geometric structure.

problem Probabilistic models often exhibit salient geometric structure.
method NBB method decomposes probability measure into manifold and normal spaces, estimates manifold as density ridge, and generates new data by bootstrapping projection vectors.
result NBB generates new data that preserves the geometric structure of a given data set.

This work classifies belted sum decompositions of fully augmented links.

problem Understanding belted sum decompositions of fully augmented links.
method Explicit classifications of thrice punctured spheres in FAL complements, geometric, combinatorial, and diagrammatic characterizations.
result Every FAL complement canonically decomposes into FALs which are either prime or two-fold covers of the Whitehead link.

Develops a statistical framework for self-supervised representation learning using data augmentation.

problem Lack of theoretical understanding of data augmentation in nonlinear settings.
method Augmentation invariant manifold learning framework and stochastic optimization algorithm.
result Improves downstream analysis by exploiting manifold's geometric structure and invariant property of augmented data.

New method learns dynamics from sparse data using geometric constraints.

problem Learning dynamics from sparse, undersampled data.
method Reformulates inference as a stochastic control problem, using geometry-driven path augmentation.
result Accurately recovers stochastic dynamics from extremely undersampled data.

The paper explores parabolic regularity in geometric variational analysis.

problem Developing calculus rules and computation formulas for second-order generalized differential constructions.
method Introducing and applying the concept of parabolic regularity to geometric aspects of second-order variational analysis.
result Established new calculus rules and computation formulas for second-order generalized differential constructions.

This work analyzes the role of data augmentation in self-supervised learning using RKHS approximation and regression.

problem Limited theoretical understanding of the role of data augmentation in self-supervised learning.
method Geometric characterization of the target function given by augmentation, proving generalization bounds.
result Two generalization bounds are derived, one free of model complexity, the other specific to near-optimal encoders.

In this paper we construct an A\mathcal{A}_\infty-category associated to a Legendrian submanifold of jet spaces. Objects of the category are augmentations of the Chekanov algebra A(Λ)\mathcal{A}(Λ) and the homology of the morphism spaces forms a new set of invariants of Legendrian submanifolds called the bilinearised Le…

2012-10-27abs ↗pdf ↗

Proposes a new framework for learning image augmentations to improve classification performance.

problem Improving classification performance with a given class of predictors.
method Transformed Risk Minimization (TRM) framework that optimizes both predictive models and data transformations.
result Performance of TRM with SCALE algorithm compares favorably to prior methods on CIFAR10/100.

In this paper, we determine geometric information on slope lengths of a large class of knots in the 3-sphere, based only on diagrammatical properties of the knots. In particular, we show such knots have meridian length strictly less than 4, and we find infinitely many families with meridian length approaching 4 from be…

2007-03-21abs ↗pdf ↗

We study the connection between topological strings and contact homology recently proposed in the context of knot invariants. In particular, we establish the proposed relation between the Gromov-Witten disk amplitudes of a Lagrangian associated to a knot and augmentations of its contact homology algebra. This also impl…

2013-04-21abs ↗pdf ↗

We propose a geometric algorithm for topic learning and inference that is built on the convex geometry of topics arising from the Latent Dirichlet Allocation (LDA) model and its nonparametric extensions. To this end we study the optimization of a geometric loss function, which is a surrogate to the LDA's likelihood. Ou…

2016-10-27abs ↗pdf ↗

Farrell and Hsiang noticed that the geometric surgery groups defined By Wall, Chapter 9, do not have the naturality Wall claims for them. They were able to fix the problem by augmenting Wall's definitions to keep track of a line bundle. The definition of geometric Wall groups involves homology with local coefficients a…

2006-06-26abs ↗pdf ↗

We investigate the geometry of hyperbolic knots and links whose diagrams have a high amount of twisting of multiple strands. We find information on volume and certain isotopy classes of geodesics for the complements of these links, based only on a diagram. The results are obtained by finding geometric information on ge…

2007-09-18abs ↗pdf ↗

Let M be a complete hyperbolic 3-manifold of finite volume that admits a decomposition into right-angled ideal polyhedra. We show that M has a deformation retraction that is a virtually special square complex, in the sense of Haglund and Wise and deduce that such manifolds are virtually fibered. We generalise a theorem…

2009-03-30abs ↗pdf ↗

We study the representation theory of the quantum Teichmueller space when going to infinity in the classical Teichmueller space. The geometric ingredients are the extension of Thurston's shear coordinates to the augmented Teichmueller space and the study of the Weil-Petersson Poisson structure for this extension. The r…

2009-11-13abs ↗pdf ↗

LLoCa makes any network Lorentz-equivariant, achieving high accuracy and efficiency.

problem Limitations of specialized layers in Lorentz-equivariant neural networks.
method LLoCa framework using local reference frames and geometric message passing.
result Models achieve competitive and state-of-the-art accuracy on particle physics tasks.

The paper connects Chern-Simons invariants to mixed Tate motives in hyperbolic 3-manifolds.

problem Understanding the relationship between Chern-Simons invariants and mixed Tate motives in hyperbolic 3-manifolds.
method Constructing a mixed Tate motive over the invariant trace field whose image equals the Chern-Simons invariant and complex volume.
result The mixed Hodge realization of the motive is a quotient of the path torsor of the augmented character variety.

Simplified geometric derivation of quantum A-polynomials for knots.

problem Deriving quantum A-polynomials for knots in a simple geometric way.
method Geometric derivation using Ward identities in Chern-Simons theory, contact geometry, and Kauffman calculus.
result Simplified presentation of quantum A-polynomials, making them accessible to a broader audience.

SymDiff uses stochastic symmetrisation for equivariant diffusion models.

problem Constructing equivariant diffusion models for data augmentation.
method Stochastic symmetrisation for lightweight, efficient, and easy-to-implement equivariance.
result SymDiff achieves significant empirical benefit for E(3)\mathrm{E}(3)-equivariant molecular generation.

PBA generates nonstationary augmentation schedules to match AutoAugment's performance with less compute.

problem Choosing an effective augmentation policy from a large search space.
method Population Based Augmentation (PBA) generates nonstationary augmentation policy schedules.
result PBA matches AutoAugment's performance on CIFAR-10, CIFAR-100, and SVHN with less compute.

Study examines how data augmentation impacts optimization in linear regression.

problem Understanding how data augmentation schedules affect optimization in linear regression.
method Analyzed the effect of augmentation on optimization in linear regression with MSE loss, using classical convex optimization and recent work on implicit bias.
result Proved that under certain joint schedules for learning rate and augmentation scheme, augmented gradient descent converges and characterized the resulting minimum.

Data augmentation doesn't improve robustness, contrary to belief.

problem The effectiveness of data augmentation in improving model robustness is questioned.
method Taking a Domain Generalization viewpoint, the study examines the robustness of augmented representations.
result Augmented representations are not robust to distortions used during training.

This paper improves auto-augment efficiency by sharing augmentation weights.

problem Efficient evaluation of augmentation policies for model training.
method Augmentation-Wise Weight Sharing (AWS) to create a fast yet accurate proxy task.
result Augmentation policies found achieve superior accuracies compared to existing methods.