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.

168,695 papers · 148 categories

Trend · papers per month

4794141188 · Jun 202019922001200920172026
48 results for function-space MAP

Defines manifolds of mappings between function spaces and discusses their properties.

problem Defining smooth manifolds of mappings between function spaces.
method Defines a smooth manifold structure on sets of continuous mappings and discusses properties of natural mappings.
result Properties of spaces of sections and smoothness of natural mappings between spaces of mappings.

Unified methodology for estimating optimal transport maps in various function spaces.

problem Estimating the function TT given samples from PP and TPT_\sharp P.
method Unified methodology based on Poincaré inequality and smooth convex function gradient.
result Nearly sharp results in various settings, including normal distribution and neural networks.

Develops a new method for functional regression that works with non-Gaussian data.

problem Limited models for regression in function spaces with Gaussian process priors.
method Introduces Neural Operator Flows (OpFlow) for non-Gaussian function spaces.
result OpFlow enables robust and accurate uncertainty quantification for functional regression.

Function-space MAP estimation leads to better generalization and robustness.

problem The mismatch between parameter posterior and function posterior in model training.
method Directly estimating the most likely function implied by the model and data.
result Function-space MAP estimation can lead to flatter minima, better generalization, and improved robustness.

Diffeologies unify infinite-dimensional geometry and PDEs, enhancing classical function spaces.

problem Combining infinite-dimensional geometry and PDEs for optimization problems.
method Review and extension of classical function spaces and mapping spaces.
result Diffeologies provide a unified framework for evolution equations and optimization problems.

Study the landscape of Lipschitz functions between manifolds using persistent homology.

problem Understanding the structure of homotopy paths between maps with high Lipschitz constants.
method Using persistent homology to analyze the landscape of Lipschitz functions between manifolds.
result First results on the persistence of higher-dimensional cycles in function spaces.

Study connects Gaussian processes and regularization for sequence-function mappings.

problem Understanding and interpreting sequence-function maps in biology.
method Relates Gaussian process priors, regularization, and gauge fixing in overparameterized weight space.
result Established the relationship between regularized regression and Gaussian processes in function space.

Convolutional layers in graph neural networks are a fundamental type of layer which output a representation or embedding of each graph vertex. The representation typically encodes information about the vertex in question and its neighbourhood. If one wishes to perform a graph centric task, such as graph classification,…

2019-05-15abs ↗pdf ↗

This work extends Gaussian process priors to neural operators for function space mappings.

problem Improving uncertainty quantification in deep neural networks.
method Extending Gaussian process priors to neural operators with conditions for convergence and computation of covariance functions.
result Arbitrary-depth neural operators with Gaussian kernels converge to function-valued GPs, enabling posterior computation in regression scenarios.

Koschorke introduced a map from the space of closed nn-component links to the ordered configuration space of nn-tuples of points in R3\mathbb{R}^3, and conjectured that this map separates homotopy links. The purpose of this paper is to construct an analogous map for string links, and to prove (1) this map in fact sep…

2015-04-13abs ↗pdf ↗

DGPFM uses deep Gaussian processes to map functions accurately and quantify uncertainty.

problem Learning mappings between functional spaces, especially when data are noisy, sparse, or irregularly sampled.
method Constructs a sequence of GP-based linear and nonlinear transformations directly in function space, leveraging kernel integral transforms, GP conditional means, and nonlinear activations sampled from Gaussian processes.
result Empirical results show DGPFM outperforms existing methods in predictive accuracy and uncertainty calibration.

Let MM be a complete metric ANRANR-space such that for any metric compactum KK the function space C(K,M)C(K,M) contains a dense set of Bing (resp., Krasinkiewicz) maps. It is shown that MM has the following property: If f ⁣:XYf\colon X\to Y is a perfect surjection between metric spaces, then C(X,M)C(X,M) with the source limitati…

2008-12-15abs ↗pdf ↗

This is the first of a series of papers which are devoted to a comprehensive theory of maps between orbifolds. In this paper, we define the maps in the more general context of orbispaces, and establish several basic results concerning the topological structure of the space of such maps. In particular, we show that the …

2006-03-29abs ↗pdf ↗

We study deep neural networks with polynomial activations, particularly their expressive power. For a fixed architecture and activation degree, a polynomial neural network defines an algebraic map from weights to polynomials. The image of this map is the functional space associated to the network, and it is an irreduci…

2019-05-29abs ↗pdf ↗

Develops methods to measure and set function-space learning rates in neural networks.

problem Measuring and optimizing changes in neural network output functions.
method Efficient methods to measure and set function-space learning rates, requiring minimal computational overhead.
result Demonstrates FLeRM (Function-space Learning Rate Matching) for hyperparameter transfer across model scales.

Paper characterizes embeddability of function spaces into LpL_p-type RKBS via metric entropy.

problem Characterizing embeddability of function spaces into LpL_p-type RKBS.
method Establishes a connection between metric entropy growth and embeddability.
result A bound on metric entropy growth allows embedding into LpL_p-type RKBS.

NEON uses neural networks to optimize functions in infinite-dimensional spaces.

problem Optimizing composite functions in function spaces.
method NEON (Neural Epistemic Operator Networks) for sequential decision-making.
result NEON achieves state-of-the-art performance with fewer parameters.

In this paper we develop the mathematics required in order to provide a description of the observables for quantum fields on low-regularity spacetimes. In particular we consider the case of a massless scalar field φφ on a globally hyperbolic spacetime MM with C1,1C^{1,1} metric gg. This first entails showing that the …

2019-10-30abs ↗pdf ↗

Study on fourth order Lamm-Riviere system for biharmonic mappings in 4D.

problem Higher order regularity and sharp Holder continuity of weak solutions.
method Optimal higher order regularity and sharp Holder continuity through analysis of the Lamm-Riviere system.
result Derive weak compactness for sequences of weak solutions with uniformly bounded energy.

In this paper we propose a function space approach to Representation Learning and the analysis of the representation layers in deep learning architectures. We show how to compute a weak-type Besov smoothness index that quantifies the geometry of the clustering in the feature space. This approach was already applied suc…

2017-10-09abs ↗pdf ↗

Gradient descent reshapes the function space of neural networks.

problem Understanding how feature learning affects the function space of neural networks.
method Characterized the evolution of the feature space during training using a two-layer neural network.
result Gradient descent induces a data-adaptive deformation that selectively enhances signal-aligned directions.

FTIP uses normalizing flows to improve posterior inference in function space.

problem Challenges in posterior inference with implicit-process priors.
method FTIP uses normalizing flows to define a richer variational distribution over combination weights.
result FTIP captures asymmetric and multimodal posterior structure better than Gaussian coefficient approximations.

We prove the projective plane $\rp^2$ is an absolute extensor of a finite-dimensional metric space XX if and only if the cohomological dimension mod 2 of XX does not exceed 1. This solves one of the remaining difficult problems (posed by A.N.Dranishnikov) in extension theory. One of the main tools is the computation …

2007-01-04abs ↗pdf ↗

A new framework learns system design using neural features in function space.

problem Learning system design with neural feature extractors.
method Introduces feature geometry in function space, nesting technique for optimal feature approximation.
result Optimal features found from data samples using off-the-shelf architectures and optimizers.

Bayesian deep learning uses function-space priors to improve model uncertainty and robustness.

problem Bayesian deep learning struggles with model-specific weight-space priors that are hard to interpret and specify.
method Apply a Dirichlet prior in predictive space and perform approximate function-space variational inference.
result The approach improves uncertainty quantification, scalability, and adversarial robustness in large-scale image classification.

Method converts neural networks to function space for better uncertainty quantification.

problem Lack of uncertainty estimates and difficulty in incorporating new data in deep neural networks.
method Dual parameterization to convert from weight space to function space, enabling sparse representation.
result Compact and principled way to capture uncertainty and incorporate new data.

Flow Annealing Posterior Sampling unifies stochastic-process regression and PDE inverse problems.

problem Function-space posterior sampling for stochastic processes and inverse problems.
method Flow Annealing Posterior Sampling (FAPS) using pretrained function-space flow-matching priors.
result Coherent posterior samples with accurate uncertainty quantification.

We say that a metrizable space MM is a Krasinkiewicz space if any map from a metrizable compactum XX into MM can be approximated by Krasinkiewicz maps (a map g ⁣:XMg\colon X\to M is Krasinkiewicz provided every continuum in XX is either contained in a fiber of gg or contains a component of a fiber of gg). In this pap…

2008-02-29abs ↗pdf ↗

We extend diffusion models to function spaces and introduce a new method for sampling from posterior distributions.

problem Sampling from posterior distributions in infinite-dimensional function spaces using diffusion models.
method Infinite-dimensional extension of Doob's hh-transform, Supervised Guidance Training for efficient sampling.
result We prove that diffusion models can be conditioned to sample from posterior distributions and introduce a simulation-free score matching objective.

Complex functional maps link tangent bundles, preserving orientation and angles.

problem Linking tangent bundles for orientation-aware correspondence.
method Endow tangent bundles with complex structures to enable robust transfer of tangent vector fields.
result Establishes orientation-aware correspondence without relying on descriptors or extra regularization.

A new machine learning method for Bayesian inverse problems in function spaces.

problem Bayesian inverse problems in function spaces with incompatibility of white noise sources.
method One-step generative transport with amortized neural operator and prior-aligned Gaussian random field.
result Generative operator trained on prior samples and noisy observations generates posterior samples efficiently.

This work uses sampling theory to analyze smoothness and error bounds of finite neural networks.

problem Analyzing the function space of finite neural networks and providing error bounds.
method Applying sampling theory to finite neural networks with non-expansive activation functions, considering both deterministic and random sampling.
result Novel error bounds for univariate neural networks under band-limited input assumption, highlighting the advantage of deterministic uniform sampling.

This work explores function-space inference using KL divergence and proposes Bayesian linear regression as a benchmark.

problem Approximating the predictive posterior distribution of Bayesian models without parameter posterior approximation.
method Employing Kullback-Leibler divergence and proposing featurized Bayesian linear regression as a benchmark.
result Minimizing KL divergence leads to an ill-defined objective function, highlighting limitations of this approach.

The paper defines function spaces on manifolds with bounded or singular geometries.

problem Defining function spaces on manifolds with various geometries.
method Introduces and analyzes Sobolev, Besov, and Bessel potential spaces on uniformly regular and singular Riemannian manifolds.
result Demonstrates maximal regularity for a linear parabolic problem on singular manifolds.

Develops local elliptic regularity for geometrically-natural operators with low regularity coefficients.

problem Local elliptic regularity for operators with low regularity coefficients in Sobolev-type spaces.
method Rescaling estimates and multiplication results for function spaces.
result Unified set of interior estimates and regularity inference for operators with Sobolev-type coefficients.

We consider a global, nonlinear version of the Whitney extension problem for manifold-valued smooth functions on closed domains CC, with non-smooth boundary, in possibly non-compact manifolds. Assuming CC is a submanifold with corners, or is compact and locally convex with rough boundary, we prove that the restrictio…

2018-01-12abs ↗pdf ↗