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.

169,291 papers · 148 categories

Trend · papers per month

13263952 · Feb 202019922001200920182026
48 results for Non-centred parameterizations

Develops efficient MCMC for Bayesian inverse problems, robust to high dimensions.

problem Efficient exploration of posterior distributions in high-dimensional latent states.
method Non-centred parameterizations and dimension-robust samplers for latent Gaussian processes.
result Framework is dimension-robust, maintaining efficiency as dimension increases.

We introduce a new GP kernel based on the sinc function for band-limited signals.

problem Designing covariance kernels for band-limited signals.
method Proposes a Gaussian process kernel with a power spectral density modeled by a rectangular function.
result The sinc kernel facilitates efficient signal processing applications like stereo modulation and band-pass filtering.

Automates reparameterization in probabilistic programs for better inference.

problem Performance of inference algorithms is affected by parameterization, requiring manual and non-intuitive transformations.
method Automates non-centring and related reparameterizations using interleaved sampling and variational formulation.
result New inference algorithms yield more efficient samplers than fixed parameterizations across various models.

Improved standard parameterization yields well-defined neural tangent kernel.

problem Extrapolation of standard parameterization to infinite width is problematic.
method Proposed an improved extrapolation of the standard parameterization.
result Improved standard parameterization yields similar accuracy to NTK parameterization but with better correspondence to finite width networks.

GANs improve stochastic parameterization of the Lorenz '96 model.

problem Improving stochastic parameterizations for sub-grid processes.
method Developed a GAN-based stochastic parameterization for the Lorenz '96 model.
result GAN configurations outperform a bespoke parameterization in skillful forecasts and climate simulations.

Parallel algorithm for conformal parameterization of 3D surfaces.

problem Computational difficulties with high-resolution 3D surface meshes.
method Partitioning surfaces into subdomains, parallel local parameterization, partial welding for boundary integration, solving Laplace equation.
result Significant improvement in computational time and accuracy compared to existing methods.

The current paper discusses some new results about conformal polynomic surface parameterizations. A new theorem is proved: Given a conformal polynomic surface parameterization of any degree it must be harmonic on each component. As a first geometrical application, every surface that admits a conformal polynomic paramet…

2012-05-25abs ↗pdf ↗

The paper analyzes how over-parameterization affects GD convergence in matrix sensing problems.

problem Matrix sensing problem with over-parameterized gradient descent.
method Analyzes symmetric and asymmetric parameterizations, provides lower bounds and convergence rates.
result Over-parameterization slows down GD convergence, but asymmetric parameterization can speed up convergence.

Novel framework for policy optimization with general parameterization and linear convergence.

problem Lack of theoretical guarantees for policy optimization with general parameterization schemes.
method Mirror descent approach for policy optimization with general parameterization.
result First result of linear convergence for policy-gradient-based method with general parameterization.

We introduce a new parameterization method for deep learning layers using spectral tensor train decomposition.

problem Efficiency and stability in deep learning models with weight matrix compression.
method Spectral Tensor Train Parameterization (STTP) of weight matrices.
result Improved compression and training stability in neural networks.

Develops a method for conformal parameterization of point clouds without fixed boundaries.

problem Desirable distortion in fixed-boundary parameterizations of point clouds.
method Free-boundary conformal parameterization method involving approximation of point cloud Laplacian and boundary treatment.
result High-quality point cloud meshing achieved through the proposed method.

Gradient descent achieves good generalization for over-parameterized deep ReLU networks.

problem Understanding good generalization in over-parameterized deep neural networks.
method Algorithm-dependent generalization error bound for deep ReLU networks using gradient descent.
result Gradient descent with proper initialization can achieve arbitrarily small generalization error for over-parameterized DNNs.

Least squares regression shows unexpected double descent in under-parameterized models.

problem Understanding the generalization of under-parameterized models in regression.
method Analyzing the spectrum and eigenvectors of the sample covariance matrix.
result Least squares regression can exhibit a peak in generalization in the under-parameterized regime, contrary to previous explanations.

The paper proposes methods for volumetric parameterization of 3D solid manifolds.

problem Complex structure of solid manifolds makes conventional approaches ineffective.
method Incorporates models to preserve geometric structure, achieve density equalization, and balance distortions.
result Various 3D manifold parameterizations with different properties can be achieved.

Study shows how over-parameterized classifiers can still perform well on noisy data.

problem Understanding how maximum margin classifiers perform in over-parameterized settings with noisy data.
method Analyzes maximum margin classifiers on sub-Gaussian mixtures, providing risk bounds.
result Characterizes conditions for 'benign overfitting' in linear classification problems.

This is a survey of the theory of complex projective (CP^1) structures on compact surfaces. After some preliminary discussion and definitions, we concentrate on three main topics: (1) Using the Schwarzian derivative to parameterize the moduli space (2) Thurston's parameterization of the moduli space using grafting (3) …

2009-02-11abs ↗pdf ↗

Gradient descent recovers low-rank matrices from corrupted measurements with double over-parameterization.

problem Robust recovery of low-rank matrices from grossly corrupted measurements.
method Gradient descent with discrepant learning rates for double over-parameterized models.
result Gradient descent with discrepant learning rates provably recovers the underlying matrix without prior knowledge on rank or sparsity.

Gradient descent slows significantly in over-parameterized single neuron learning.

problem Learning a single neuron with over-parameterization and square loss.
method Analysis of gradient descent dynamics, proving convergence rates and lower bounds.
result Over-parameterization can exponentially slow down the convergence rate of gradient descent.

New framework for better mapping of surfaces onto ellipsoids.

problem Mapping genus-0 closed surfaces onto spheres results in large distortion.
method Combining conformal and quasi-conformal mappings onto ellipsoids.
result Achieved a variety of ellipsoidal parameterizations with bijectivity.

This paper explores adaptive methods in over-parameterized linear regression.

problem Understanding why neural networks generalize well in over-parameterized settings.
method Characterizes two sub-classes of adaptive methods and their generalization performance.
result Adaptive methods in over-parameterized linear regression converge to the minimum norm solution.

New methods solve tensor-on-tensor regression with unknown rank, revealing benefits of over-parameterization.

problem Connecting tensor responses to tensor covariates with unknown intrinsic rank.
method Riemannian gradient descent and Riemannian Gauss-Newton methods for tensor-on-tensor regression.
result Riemannian optimization methods converge linearly and quadratically to a statistically optimal estimate in rank over-parameterized settings.

New framework explains why over-parameterized neural networks work well.

problem Why over-parameterized neural networks perform well in practice.
method Neural feature repopulation framework using gradient descent.
result Over-parameterized two-level neural networks learn near optimal feature distributions.

Local PCA detects intrinsic parameterization of complex thermo-chemical state-spaces.

problem Detecting intrinsic parameterization of complex thermo-chemical state-spaces.
method Local PCA applied to local clusters of data.
result Local PCA finds meaningful parameterization linked to local stoichiometry, reaction progress, and soot formation processes.

Local convergence theory for mildly over-parameterized neural nets.

problem Understanding why over-parameterization works in neural networks.
method Developed a local convergence theory for two-layer neural nets, showing neuron convergence under certain conditions.
result All student neurons converge to one of teacher neurons when the loss is below a threshold.

Novel approach analyzes ReLU networks' training dynamics and proposes GmP for improved optimization.

problem Stochastic optimization instability in ReLU networks impedes convergence and generalization.
method Characteristic activation boundaries analysis and Geometric Parameterization (GmP) technique.
result GmP resolves instability, leading to better optimization, convergence, and generalization.

Improves observation-driven filters using proper scoring rules for better parameter estimation.

problem Improves parameter estimation in observation-driven filters.
method Replaces likelihood score with negative parameter derivative of a proper scoring rule.
result Establishes consistency and asymptotic normality for estimation.

This work improves the lottery ticket hypothesis by reducing over-parameterization requirement.

problem Approximating a neural network by pruning a randomly over-parameterized network.
method Connecting pruning ReLU networks to extsc{SubsetSum} problem, showing logarithmic over-parameterization sufficiency.
result Logarithmic over-parameterization is sufficient for approximating any target neural network.

This paper presents a method to compute the {\it quasi-conformal parameterization} (QCMC) for a multiply-connected 2D domain or surface. QCMC computes a quasi-conformal map from a multiply-connected domain SS onto a punctured disk DSD_S associated with a given Beltrami differential. The Beltrami differential, which me…

2014-03-26abs ↗pdf ↗

Developed an ellipsoidal density-equalizing map for genus-0 closed surfaces.

problem Large geometric distortion when using spherical domain for genus-0 closed surfaces.
method Developed a novel method for ellipsoidal density-equalizing maps and combined with quasi-conformal maps.
result Significantly improved surface remeshing performance for genus-0 closed surfaces.

The paper introduces new curvature flows and uniformization theorems for polyhedral surfaces.

problem Discrete uniformization and rigidity of polyhedral surfaces.
method Parameterized discrete curvature, uniformization theorem, Yamabe flow, Calabi flow.
result The flows converge to metrics with constant discrete curvature, confirming conjectures.

Surface parameterizations have been widely used in computer graphics and geometry processing. In particular, as simply-connected open surfaces are conformally equivalent to the unit disk, it is desirable to compute the disk conformal parameterizations of the surfaces. In this paper, we propose a novel algorithm for the…

2014-08-29abs ↗pdf ↗