Spheres' spectral structure converges to Gaussian space's as dimensions grow.
problem Understanding spectral convergence between high-dimensional spheres and Gaussian spaces.
method Proving spectral convergence using projections and eigenvalues.
result Spectral structure on high-dimensional spheres converges to Gaussian space's as dimensions increase.
Proves convergence of normal forms for infinite-dimensional Lie pseudo-group actions.
problem Analyzing convergence of normal forms for complex manifolds.
method Equivariant moving frame method and Cartan-Kähler Theorem.
result Proves convergence of normal form power series for infinite-dimensional Lie pseudo-group actions.
The paper proves stability in compact finite dimensional Alexandrov spaces using equivariant Gromov--Hausdorff convergence.
problem Stability in compact finite dimensional Alexandrov spaces.
method Equivariant Gromov--Hausdorff convergence and almost commutative diagrams.
result Stability result in compact finite dimensional Alexandrov spaces.
Proofs high-dimensional spectrum convergence of weighted sample covariance.
problem High-dimensional spectrum convergence of weighted sample covariance.
method Proposes a new, concise proof with stronger assumptions.
result Spectrum convergence proven for different weight distributions.
Study introduces fractional mass concept for surfaces, proving its convergence.
problem Understanding fractional mass on surfaces.
method Introduces fractional s-mass, proves Γ-convergence and pointwise convergence. result Fractional s-mass converges to (n−2)-dimensional area. pHMC converges on infinite-dimensional spaces with bounds.
problem Convergence of pHMC on Hilbert spaces.
method Coupling of two pHMC copies, adapted from arXiv:1805.00452.
result Proven convergence bounds in 1-Wasserstein distance.
Machine learning improves high-dimensional matrix estimation.
problem Efficient estimation of high-dimensional matrices.
method Integrates machine learning with classical optimization algorithms for high-dimensional matrix estimation.
result The reparameterized LADMM achieves faster convergence and higher accuracy.
Smooth DNNs mitigate the curse of dimensionality in uniform convergence for various regression tasks.
problem The curse of dimensionality in uniform convergence of ReLU networks.
method Analysis of smoothly activated deep neural networks (smooth DNNs), establishing pseudo-dimension bounds and non-asymptotic approximation guarantees.
result Smooth DNNs achieve non-asymptotic uniform convergence rates across multiple statistical contexts, mitigating the curse of dimensionality.
Ellipsoids approach Gaussian distribution in high dimensions.
problem Understanding convergence of high-dimensional ellipsoids to Gaussian spaces.
method Proof of convergence in Gromov's concentration topology.
result Solid ellipsoids converge to Gaussian space in high dimensions.
Gradient flow of ReLU networks converges in low-correlation high-dimensional data.
problem Convergence of shallow ReLU networks trained on weakly interacting data.
method Gradient flow analysis with Polyak-Łojasiewicz viewpoint.
result Network width of order log(n) neurons suffices for global convergence with high probability.
Deep learning method proves convergence for high-dimensional PDEs.
problem Solving high-dimensional nonlinear PDEs for mean field control problems.
method Deep Galerkin method (DGM) for Hamilton-Jacobi-Bellman (HJB) equations.
result DGM converges to the true value function of mean field control problems.
New rates for GLD and SGLD in infinite-dimensional spaces without dimensionality issues.
problem Gradient Langevin dynamics and SGLD convergence rates in high-dimensional spaces.
method Analysis of GLD and SGLD in infinite-dimensional Hilbert spaces, using stochastic differential equations and Markov chains.
result Derivation of dimension-free convergence rates for GLD and SGLD.
Tensor networks improve integration accuracy for high-dimensional problems.
problem Integration of high-dimensional functions with exponential convergence.
method Regression-free tensor network representations for integration.
result Exponential convergence achieved for non-analytic integrands.
New metrics avoid high-dimensional analysis challenges, proving convergence without 'curse of dimensionality'.
problem High-dimensional analysis challenges in empirical measure convergence.
method Proposed a new class of probability metrics free of the curse of dimensionality.
result Convergence of empirical measures is free of the curse of dimensionality.
Investigates how SGD behaves in high-dimensional neural networks, distinguishing between global convergence and local minima.
problem Understanding the behavior of SGD in high-dimensional shallow neural networks.
method Extends statistical physics analysis to study SGD dynamics, focusing on mean-field/hydrodynamic regime and learning rate.
result Identifies the critical number of hidden units and learning rate for SGD to avoid local minima.
Improved score matching methods for estimating score functions and Hessians without high dimensionality.
problem Estimating score functions and Hessians efficiently in high-dimensional data.
method Implicit score matching and denoising score matching, leveraging Gagliardo-Nirenberg inequalities.
result Achieves convergence rates similar to denoising score matching and estimates Hessians without dimensionality issues.
The paper shows diffusion models can converge faster to a target distribution with low-dimensional structure.
problem Improving the convergence rate of diffusion models to target distributions.
method Analyzing DDIM and DDPM samplers under low-dimensional structure assumptions.
result The iteration complexities of DDIM and DDPM are no greater than k/ε in total variation distance. Online learning of linear operators between infinite-dimensional spaces is possible but with limitations.
problem Learning linear operators between infinite-dimensional Hilbert spaces in an online setting.
method Online learning approach for linear operators with bounded p-Schatten norm, proving impossibility for operator norm. result Separation between online learnability and uniform convergence for bounded linear operators.
Improved KL bounds and Wasserstein guarantees for diffusion flow matching under minimal conditions.
problem Theoretical convergence properties of Brownian motion based diffusion flow matching.
method Refined analysis under Kullback-Leibler and 2-Wasserstein distances.
result State-of-the-art scaling in KL convergence bounds under minimal conditions.
Local Bayesian optimization shows strong performance and converges well, contrary to folklore.
problem Understanding the behavior and convergence of local Bayesian optimization methods.
method Studied the behavior of local optimization strategies and rigorously analyzed a specific algorithm.
result Local Bayesian optimization algorithms converge well and perform strongly, contrary to the folklore.
We associate certain probability measures on R to geodesics in the space $\H_L$ of positively curved metrics on a line bundle L, and to geodesics in the finite dimensional symmetric space of hermitian norms on H0(X,kL). We prove that the measures associated to the finite dimensional spaces converge weakly to t…
This work studies the smooth 1-Wasserstein distance and its limit distribution in high dimensions.
problem Addressing the curse of dimensionality in empirical approximation.
method Conducts a statistical study including limit distribution, bootstrap consistency, and concentration inequalities.
result Derives a nondegenerate limit distribution for empirical SWD, contrasting with classic W1. Convolutional neural networks improve image classification accuracy.
problem Improving accuracy in image classification.
method Analyzing the convergence rate of misclassification risk for image classifiers.
result A rate of convergence independent of image dimension proves the effectiveness of CNNs.
The paper extends kernel ridge regression to product kernels and reveals new convergence behaviors.
problem Understanding kernel ridge regression in large dimensions with various kernels.
method Established a broad family of large dimensional kernels and derived convergence rates.
result Revealed new phenomena including minimax optimality, saturation effect, and multiple descent behavior.
Diffusion models converge linearly to complex data manifolds.
problem Sampling from high-dimensional complex data distributions.
method Score-matching generative models with novel integration scheme.
result Linear convergence in KL divergence to intrinsic dimension d. A new method for faster optimization in high dimensions.
problem Slow convergence in high-dimensional optimization problems.
method Subspace cubic regularized Newton method within Krylov subspace.
result Achieves a dimension-independent convergence rate of O(1/mk + 1/k^2).
Many statistical M-estimators are based on convex optimization problems formed by the combination of a data-dependent loss function with a norm-based regularizer. We analyze the convergence rates of projected gradient and composite gradient methods for solving such problems, working within a high-dimensional framewor…
Paper studies t-SNE convergence with generalized kernels.
problem Understanding convergence of t-SNE with generalized kernels.
method Concrete formulation of generalized kernels, proving convergence to an equilibrium distribution.
result t-SNE converges to an equilibrium distribution under certain conditions for generalized kernels.
The paper develops a uniform function estimator in RKHS for regression.
problem Reconstructing functions from noisy data at random locations.
method Using reproducing kernel Hilbert spaces and Gaussian random fields.
result The estimator converges uniformly to the conditional expectation.
Let X=M×E where M is an m-dimensional Kähler manifold with negative first Chern class and E is an n-dimensional complex torus. We obtain C∞ convergence of the normalized Kähler-Ricci flow on X to a Kähler-Einstein metric on M. This strengthens a convergence result of Song-Weinkove and con…
We investigate the prediction capability of the orthogonal greedy algorithm (OGA) in high-dimensional regression models with dependent observations. The rates of convergence of the prediction error of OGA are obtained under a variety of sparsity conditions. To prevent OGA from overfitting, we introduce a high-dimension…
In the present paper, we determine the topologies of three-dimensional closed Alexandrov spaces which converge to lower dimensional spaces in the Gromov-Hausdorff topology.
New theorem for generalized group sparsity improves consistency and convergence rates.
problem Improving statistical inference in high-dimensional data with element-wise and group-wise sparsity.
method Developed a generalized version of Sparse-Group Lasso and proved a universal theorem for consistency and convergence rates.
result Obtained results on consistency and convergence rates for different forms of double sparsity regularization.
The paper explains how ReLU nets converge globally in high dimensions without strict assumptions.
problem Understanding global convergence of ReLU nets in very high dimensions.
method Fine-grained analysis of random activation matrices and detailed gradient norm and curvature analysis.
result Empirical loss function has favorable geometrical properties in the overparameterized setting.
Spectral algorithms on manifolds using diffusion kernels improve convergence rates.
problem The limitations of existing spectral algorithms in RKHSs for data on manifolds.
method Integrating manifold structure into spectral algorithms using heat kernel diffusion spaces.
result Spectral algorithms converge to the target function and its derivatives in a strong sense, with rates dependent on manifold intrinsic dimension.
MFCNs use sparse graphs to approximate manifold convergence.
problem Understanding manifold neural networks (MNNs).
method Sparse graph approximation for manifold convergence.
result Method converges to continuum limit as data points increase.
The paper provides convergence guarantees for ODE-based generative models using transformers.
problem Theoretical guarantees for ODE-based generative models.
method A pre-trained autoencoder maps inputs to a latent space, and a transformer predicts the velocity field.
result The distribution of samples generated via estimated ODE flow converges to the target distribution in Wasserstein-2 distance.
Scaling Bayesian optimisation (BO) to high-dimensional search spaces is a active and open research problems particularly when no assumptions are made on function structure. The main reason is that at each iteration, BO requires to find global maximisation of acquisition function, which itself is a non-convex optimizati…
Paper analyzes Langevin dynamics for solving infinite-dimensional Bayesian inverse problems.
problem Solving high-dimensional Bayesian inverse problems in infinite-dimensional function spaces.
method Preconditioned Langevin dynamics with score-based generative models (SGMs).
result Derives error estimates and sufficient conditions for global convergence in Kullback-Leibler divergence.
Empirical Bayes rates via variational approximations and prior decomposition.
problem Nonparametric and high-dimensional inference convergence rates.
method Variational perspective and prior decomposition.
result Empirical Bayes posterior rates derived from variational Bayes.
Gaussian processes (GPs) provide flexible distributions over functions, with inductive biases controlled by a kernel. However, in many applications Gaussian processes can struggle with even moderate input dimensionality. Learning a low dimensional projection can help alleviate this curse of dimensionality, but introduc…
We consider contracting flows in (n+1)-dimensional hyperbolic space and expanding flows in (n+1)-dimensional de Sitter space. When the flow hypersurfaces are strictly convex we relate the contracting hypersurfaces and the expanding hypersurfaces by the Gauss map. The contracting hypersurfaces shrink to a point $x_0…
New algorithms improve sampling from complex distributions.
problem Sampling from high-dimensional target distributions with super-linearly growing potentials.
method Proposed aHOLA and aHOLLA algorithms with non-asymptotic convergence bounds.
result Achieved state-of-the-art rates of convergence in non-convex settings.
Study on surfaces pinched by curvature in space forms converging under specific conditions.
problem Investigating convergence of surfaces pinched by curvature in space forms.
method Proving convergence theorems for surfaces pinched by normal curvature in 4-dimensional space forms.
result Generalizes Baker-Nguyen's convergence theorem for surfaces pinched by curvature.
Paper proves convergence of Gini index to equilibrium in Wasserstein distance.
problem Proving convergence of Gini index to equilibrium in Wasserstein distance.
method Analyzes Gini index as Lyapunov functional and proves convergence in Wasserstein distance.
result Proves convergence of Gini index to equilibrium in Wasserstein distance.
Improved location estimation for high-dimensional data with finite sample size.
problem Estimating the shift in high-dimensional data with limited samples.
method Smoothed estimators and bounds on subgamma vectors.
result Convergence to Cramér-Rao bound for finite sample sizes.
Study on Metropolis-within-Gibbs schemes for high-dimensional Bayesian models.
problem Improving the scalability of MCMC methods for complex Bayesian models.
method Relating convergence properties to conditional conductance for non-conjugate hierarchical models.
result Established dimension-free convergence results for Metropolis-within-Gibbs schemes.
Study on sensor fusion algorithms under high dimensional noise.
problem Behavior of sensor fusion algorithms under high dimensional noise.
method Analysis of NCCA and AD algorithms using Gaussian kernel.
result Robustness of NCCA and AD to high dimensional noise depends on SNR and bandwidth selection.