We define gauge transformations of Jacobi structures on a manifold. This is related to gauge transformations of Poisson structures via the Poissonization. Finally, we discuss how the contact structure of a contact groupoid is effected by a gauge transformation of the Jacobi structure on its base.
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.
168,695 papers · 148 categories
Trend · papers per month
48 results for “structural transformation”
Resurgence of Joyce structures gauged to a standard form using gauge transformations.
problem Resurgence of Joyce structures in complex hyperkähler geometry.
method Gauge transformations and Borel transforms to show resurgent behavior.
result Established the resurgent behavior of infinitesimal gauge transformations for Joyce structures.
ETC improves Transformer models for long and structured inputs.
problem Scaling input length and encoding structured inputs in Transformers.
method Introduces global-local attention, relative position encodings, and CPC pre-training.
result Achieves state-of-the-art results on four natural language datasets.
Transformer learns graph structure better with subgraph info.
problem Transformer struggles with structural similarity in graph learning.
method Structure-Aware Transformer with subgraph attention.
result Improves graph prediction benchmarks significantly.
Conditions for Penrose-Ward transformation on specific manifolds.
problem Conditions for Penrose-Ward transformation on almost -manifolds with almost twistorial structures.
method Necessary and sufficient conditions derived through Penrose-Ward transformation.
result Conditions for Penrose-Ward transformation on almost -manifolds with almost twistorial structures.
We construct an infinite sequence of projectively flat manifolds by using castling transformations of prehomogeneous vector spaces. We also give a classification of manifolds equipped with a flat projective structure obtained by a finite number of castling transformations, and describe these flat projective structures …
Transformers learn causal structure through gradient descent on self-attention mechanisms.
problem Understanding how transformers learn causal structure during training.
method In-context learning task and simplified two-layer transformer model.
result Gradient descent on a simplified transformer learns to encode latent causal graphs.
A great number of deep learning based models have been recently proposed for automatic music composition. Among these models, the Transformer stands out as a prominent approach for generating expressive classical piano performance with a coherent structure of up to one minute. The model is powerful in that it learns ab…
The classical Liouville Theorem on conformal transformations determines local conformal transformations on the Euclidean space of dimension . Its natural adaptation to the general framework of Riemannian structures is the 2-rigidity of conformal transformations, that is such a transformation is fully determined…
Graded Transformerscs.LG
Graded Transformers embed algebraic structure in neural networks through graded transformations.
problem Efficiently modeling hierarchical and structured data in neural networks.
method Introduces Linearly Graded Transformer (LGT) and Exponentially Graded Transformer (EGT) with graded scaling operators.
result Establishes rigorous guarantees and improved efficiency for structured data.
Fast linear transforms are ubiquitous in machine learning, including the discrete Fourier transform, discrete cosine transform, and other structured transformations such as convolutions. All of these transforms can be represented by dense matrix-vector multiplication, yet each has a specialized and highly efficient (su…
Tracr compiles programs into transformer models for interpretability.
problem Uncertainty in understanding transformer model outputs due to unknown learned programs.
method Tracr compiles human-readable programs into known structure transformer models.
result Known structure of Tracr-compiled models serves as ground-truth for interpretability.
Graph transformers outperform graph convolutions by preserving community information.
problem Understanding why graph transformers perform well in node-level prediction tasks.
method Analyzing the Gaussian process limits of graph transformers with infinite width and infinite heads.
result Graph transformers maintain discriminative node representations even in deep layers, preventing oversmoothing.
We define spin frames, with the aim of extending spin structures from the category of (pseudo-)Riemannian manifolds to the category of spin manifolds with a fixed signature on them, though with no selected metric structure. Because of this softer requirements, transformations allowed by spin frames are more general tha…
StrTransformer recovers sources without labels by optimizing latent matrices and enforcing structural constraints.
problem Unsupervised blind source recovery in signal processing.
method Source-wise structured Transformer framework with latent source matrix optimization, structural regularization, and branch-specific weights.
result StrTransformer learns distinct temporal-scale structures and recovers source-aligned latent trajectories.
GTA improves transformer-based NVS models by encoding geometric structure.
problem Suboptimal positional encoding for 3D vision tasks.
method Geometry-aware attention mechanism encoding geometric structure of tokens.
result GTA improves learning efficiency and performance of NVS models.
Learning Generalized Transformation Equivariant Representations via Autoencoding Transformationscs.CV
Transformation Equivariant Representations (TERs) aim to capture the intrinsic visual structures that equivary to various transformations by expanding the notion of {\em translation} equivariance underlying the success of Convolutional Neural Networks (CNNs). For this purpose, we present both deterministic AutoEncoding…
Deep generative networks have been widely used for learning mappings from a low-dimensional latent space to a high-dimensional data space. In many cases, data transformations are defined by linear paths in this latent space. However, the Euclidean structure of the latent space may be a poor match for the underlying lat…
The paper explores geometric aspects of Miura transformations in integrable systems.
problem Relating different integrable equations and classifying bi-Hamiltonian structures.
method Construction of generalized Miura transformations under algebraic and geometric settings.
result Miura transformations relate integrable curve flows in different geometries and induce moving frame transitions.
Linear attention in Transformers can be interpreted as dynamic VAR models.
problem Misalignment between Transformers and autoregressive forecasting objectives.
method Interpreting linear attention as VAR, rearranging MLP, attention, and flow.
result SAMoVAR improves performance, interpretability, and efficiency.
Study on contact Hamiltonian functions for singular contact structures.
problem Understanding infinitesimal contact transformations on singular contact structures.
method Showed injectivity and provided an explicit local formula for the inverse map.
result Explicit local formula for the inverse map when contact structure has singularities of the first type.
Researchers found a Calabi-Yau structure and constructed a Bargmann type transformation on the Cayley projective plane.
problem Existence of Calabi-Yau structure and construction of Bargmann type transformation.
method Pairing of polarizations, natural Lagrangian foliation, and Kähler structure.
result Quantization of geodesic flow through elliptic Fourier integral operators.
Deep Learning: A Tutorialstat.ML
Deep learning uses layers of transformations to predict structured data with uncertainty.
problem Predicting structured high-dimensional data efficiently and with uncertainty.
method Applying layers of semi-affine input transformations to find features for probabilistic statistical methods.
result Achieves scalable prediction rules with uncertainty quantification and feature selection.
Geometric structures on quaternionic unit ball for slice regular Möbius transformations.
problem No new problem introduced.
method Introducing Hermitian, Riemannian, and Kähler-like structures on quaternionic unit ball using regular Möbius transformations.
result Geometric structures are natural generalizations of complex setup and solve problems not achieved by other geometries.
TEAFormers preserve multi-dimensional time series structures for better forecasting.
problem Traditional Transformers flatten multi-dimensional time series data, losing critical multi-dimensional relationships.
method Tensor-Augmented Transformer (TEAFormer) with Tensor-Augmentation (TEA) module.
result Significant performance enhancements in time series forecasting across benchmarks.
We prove that under certain linear reciprocal transformation, an evolutionary PDE of hydrodynamic type that admits a bihamiltonian structure is transformed to a system of the same type which is still bihamiltonian.
The paper classifies complex Dirac structures on flag manifolds.
problem Classifying invariant complex Dirac structures on flag manifolds.
method Described using roots of the Lie algebra and classified under -transformations.
result All invariant complex Dirac structures with constant real index on a maximal flag manifold are described.
Transformers learn topic structure through embedding and attention mechanisms.
problem Understanding how transformers capture semantic structure in text.
method Combination of mathematical analysis and experiments on Wikipedia and synthetic data.
result Embedding and attention layers encode topic structure in transformers.
It is shown that the heat operator in the Hall coherent state transform for a compact Lie group is related with a Hermitian connection associated to a natural one-parameter family of complex structures on . The unitary parallel transport of this connection establishes the equivalence of (geometric) quantizati…
The paper explores a B-field transform of complex structures on complex tori.
problem Deforming complex structures on complex tori using B-field transformations.
method Constructing holomorphic line bundles with integrable connections and interpreting them as deformations of complex tori by flat gerbes.
result Homological mirror symmetry between deformed and original complex tori.
We classify the simplest rational elements in a twisted loop group, and prove that dressing actions of them on proper indefinite affine spheres give the classical Tzitzéica transformation and its dual. We also give the group point of view of the Permutability Theorem, construct complex Tzitzéica transformations, and di…
Standard Transformers approximate Hölder functions and achieve optimal nonparametric regression rate.
problem Approximating Hölder functions and achieving optimal nonparametric regression rate with Transformers.
method Using the size tuple and dimension vector metrics, the paper characterizes Transformer structures and derives upper bounds for their Lipschitz constant and memorization capacity.
result Standard Transformers achieve the minimax optimal rate in nonparametric regression for Hölder target functions.
We extend the Falceto-Zambon version of Marsden-Ratiu Poisson reduction to Poisson quasi-Nijenhuis structures with background on manifolds. We define gauge transformations of Poisson quasi-Nijenhuis structures with background, study some of their properties and show that they are compatible with reduction procedure. We…
QP perspective on Poisson-Lie T-duality topology changes.
problem Understanding Poisson-Lie T-duality through QP manifolds.
method QP manifolds and canonical transformations for symplectic reductions.
result Canonical transformations mediate Poisson-Lie T-duality.
We study gauge transformations of Dirac structures and the relationship between gauge and Morita equivalences of Poisson manifolds. We describe how the symplectic structure of a symplectic groupoid is affected by a gauge transformation of the Poisson structure on its identity section, and prove that gauge-equivalent in…
In this paper, we propose several dictionary learning algorithms for sparse representations that also impose specific structures on the learned dictionaries such that they are numerically efficient to use: reduced number of addition/multiplications and even avoiding multiplications altogether. We base our work on facto…
Researchers present and compare different representations of dissipative Hamiltonian DAE systems.
problem Understanding and transforming dissipative Hamiltonian DAE systems.
method Global geometric and algebraic points of view, translations between representations, characterizations, and numerical methods for computing structural information.
result A general DAE system can be transformed into a dissipative Hamiltonian or port-Hamiltonian DAE system.
The inference of deep hierarchical models is problematic due to strong dependencies between the hierarchies. We investigate a specific transformation of the model parameters based on the multivariate distributional transform. This transformation is a special form of the reparametrization trick, flattens the hierarchy a…
The notion of generalized almost paracontact structure on the generalized tangent bundle is introduced and its properties are investigated. The case when the manifold carries an almost paracontact metric structure is also discussed. Conditions for its transformed under a - or a -field transfor…
We break down transformer embeddings into interpretable components revealing hidden geometric structures.
problem Understanding the hidden geometry and interpretability of transformer models.
method Decomposed transformer embeddings into position, context, and residual components.
result Pervasive mathematical structure in transformer embeddings, including position and context vectors.
The paper models musical motif transformations in Beethoven's works.
problem Understanding how motifs transform in symbolic music.
method Developed a probabilistic framework using Conditional Random Fields.
result Identified patterns of motif transformations and their co-occurrences.
Deep structured models are widely used for tasks like semantic segmentation, where explicit correlations between variables provide important prior information which generally helps to reduce the data needs of deep nets. However, current deep structured models are restricted by oftentimes very local neighborhood structu…
Algorithm finds optimal affine transformation to minimize overall distortion.
problem Minimizing distortion in affine transformations.
method Riemannian geometry approach to define and minimize distortion.
result Mean distorting transformation found for minimizing overall distortion.
The architecture of Transformer is based entirely on self-attention, and has been shown to outperform models that employ recurrence on sequence transduction tasks such as machine translation. The superior performance of Transformer has been attributed to propagating signals over shorter distances, between positions in …
We study several problems concerning conformal transformation on metric measure spaces, including the Sobolev space, the differential structure and the curvature-dimension condition under conformal transformations. This is the first result about preservation of lower curvature bounds under perturbation, which is new ev…
CRATE-MAE learns structured representations from unlabeled data.
problem Learning structured representations from unlabeled data.
method Structured Diffusion with White-Box Transformers.
result CRATE-MAE achieves highly promising performance on large-scale imagery datasets.
An index formula is proposed for contact transformations between contact manifolds equipped with CR structures or with fillings by symplectic manifolds. The formula generalizes the Atiyah-Singer formula and gives a conjectured formula for the index of Fourier integral operators, as well as Epstein's relative index for …
We give geometric explanations and proofs of various mirror symmetry conjectures for -invariant Calabi-Yau manifolds when instanton corrections are absent. This uses fiberwise Fourier transformation together with base Legendre transformation. We discuss mirror transformations of (i) moduli spaces of complex stru…