New divergences help audit DP in high dimensions.
problem Challenges in auditing DP in high-dimensional data.
method Propose kernel Rényi divergence and its regularized version for auditing.
result Regularized kernel Rényi divergence can be estimated from samples in high dimensions.
Paper proves rigidity for Einstein metrics in high dimensions.
problem Einstein metrics on high-dimensional manifolds.
method Liouville type rigidity result for asymptotically hyperbolic metrics.
result Established a rigidity theorem for d≥5. In high dimensions, the mean and geometric median are nearly identical.
problem Understanding the relationship between mean and geometric median in high-dimensional spaces.
method Analytical derivation and simulation of the distance between mean and geometric median.
result The distance between mean and geometric median vanishes with dimensionality in high dimensions.
High-dimensional kernel regression struggles due to rotational invariance.
problem Kernel ridge regression struggles in high dimensions due to rotational invariance.
method Analysis of kernel properties and their impact on high-dimensional data.
result Lower bound on generalization error for high-dimensional kernel regression.
Optimal bounds found for torus curvatures in high dimensions.
problem Finding optimal bounds on normal curvatures of tori.
method Analyzing immersed n-torus in a Euclidean ball of large dimension.
result Optimal bounds on normal curvatures of tori established.
The abstract discusses detecting knotted spheres through their traces in high dimensions.
problem Detecting knotted spheres in high-dimensional spaces.
method Generalizing the RBG link construction to all dimensions and using surgery.
result Existence of non-isotopic smooth (n−2)-knots with diffeomorphic traces. Neural estimator improves mutual information estimation in high dimensions.
problem Estimating mutual information in high dimensions is challenging.
method Parametrizing conditional densities with normalizing flows and using block autoregressive structure.
result Improved mutual information estimation on benchmark tasks.
K-means fails catastrophically in high dimensions, Hartigan's avoids it.
problem K-means algorithm's failure in high-dimensional data.
method Proof of k-means failure and Hartigan's algorithm success.
result Hartigan's algorithm avoids the catastrophic failure of k-means in high dimensions.
Dynamic risk factor model improves portfolio performance in high dimensions.
problem Dynamic portfolio allocation in high-dimensional financial markets.
method Time-varying sparsity on factor loadings, sequential learning of parameters and volatilities.
result Significant portfolio performance improvements and higher utility gains.
Paper connects geometric structures to algebra in high dimensions.
problem Understanding geometric structures in high dimensions.
method Relating minimal left ideals on Clifford algebras to geometric structures.
result Established a connection between algebraic and geometric properties.
New method estimates robust mean in high dimensions with minimized outliers.
problem Estimating the mean in high dimensions when a fraction of data is corrupted.
method Formulating the problem as ℓ0-norm minimization under second moment constraints, and using ℓ1 and ℓp minimization techniques. result The proposed method achieves order optimal robust mean estimation and significantly outperforms existing methods.
New scalable algorithm estimates barycenters of measures in high dimensions.
problem Estimating barycenters of measures in high-dimensional settings.
method Optimizes generative models to estimate barycenters, scaling by introducing inductive biases.
result First scalable method to estimate barycenters in thousands of dimensions.
New ACV method speeds up CV in high dimensions with approximate low-rank data.
problem Accurate model assessment in high-dimensional, large data settings with expensive algorithms.
method Developed a new ACV algorithm that uses low-rank approximations of the Hessian matrix.
result The new method is fast and accurate in the presence of approximate low-rank data.
Adaptive kernel density estimation improves accuracy in high dimensions.
problem Challenges in high-dimensional density estimation with traditional methods.
method Pre-training a neural network to recommend location-adaptive kernels.
result Effective density estimation in high dimensions with improved accuracy.
Vanilla Bayesian optimization performs well in high dimensions.
problem Bayesian optimization's poor performance in high-dimensional problems.
method Identified and addressed degeneracies, proposed scaling of Gaussian process lengthscale prior.
result Vanilla Bayesian optimization outperforms existing algorithms in high-dimensional tasks.
Non-vanishing steady Euler flows and Beltrami fields found in high dimensions.
problem Existence of non-vanishing steady Euler flows and Beltrami fields in high dimensions.
method Using open books, proved existence of non-vanishing steady solutions to the Euler equations for vector fields in odd dimensions.
result Existence of non-vanishing steady Euler flows and Beltrami fields in high dimensions.
Single Index Models (SIMs) are simple yet flexible semi-parametric models for classification and regression. Response variables are modeled as a nonlinear, monotonic function of a linear combination of features. Estimation in this context requires learning both the feature weights, and the nonlinear function. While met…
Symbolic dynamics for flows in high dimensions, extending previous work.
problem Coding flows with positive speed in high dimensions.
method Construct symbolic dynamics for flows with positive speed in any dimension.
result Extended symbolic dynamics to flows in high dimensions, including homoclinic classes.
PANDA improves linear discriminant analysis in high dimensions with minimal tuning.
problem Linear discriminant analysis in high-dimensional settings.
method PANDA: a tuning-insensitive method for linear discriminant analysis.
result PANDA achieves optimal convergence rates in estimation error and misclassification rate.
Equations for minimal surfaces from rigid motions in high dimensions.
problem Finding minimal surfaces from rigid motions in RN. method Derives equations for minimal surfaces using rigid motions in RN. result Equations for minimal surfaces in RN. Study local minimizers of Ginzburg-Landau functionals in high dimensions, showing energy measures converge to rectifiable measures.
problem Investigating minimizers of Ginzburg-Landau functionals in high dimensions with energy bounds.
method Analyzing minimizers with logarithmic energy bounds and considering the vacuum manifold's homotopy classes.
result Normalized energy measures converge to an (n−2)-rectifiable measure associated with a stationary varifold. Thompson Sampling fails to perform well in high dimensions.
problem Thompson Sampling's suboptimality in high-dimensional combinatorial semi-bandits.
method Analysis of TS for combinatorial semi-bandits, including non-linear and linear reward functions, with Bernoulli rewards and uniform priors.
result TS's regret scales exponentially in the ambient dimension and minimax regret scales almost linearly in high dimensions.
SMTM improves MCMC sampling in high dimensions with multiple proposals and stereographic integration.
problem Improving MCMC performance in high-dimensional sampling.
method Integrating multiple-try Metropolis with stereographic MCMC framework.
result SMTM outperforms classical MTM and other methods in high-dimensional sampling.
A new method for signal recovery in high dimensions using projections and diffusion models.
problem Recovering a latent signal from noisy observations with unknown support.
method Metric projection estimator based on score matching in a diffusion model.
result The posterior distribution concentrates near the metric projection of the observed signal.
Enhances anomaly detection in high dimensions with pretrained networks.
problem Difficult to characterize anomaly in high-dimensional data.
method Residual adaptation to adjust pretrained networks for anomaly detection.
result Significantly outperforms existing methods on anomaly detection benchmarks.
Polytopes in high dimensions have at least 2n+4 normals.
problem Understanding normals to convex polytopes in high dimensions.
method Proved for generic simple polytopes in R^n, n>3.
result Each polytope contains a point with at least 2n+4 normals.
Paper shows how to use geometric median for robust SGD in high dimensions.
problem Robustifying SGD for high-dimensional optimization problems with gross corruption.
method Applying geometric median to only chosen blocks of coordinates at a time.
result Retains optimal breakdown point of 0.5 for smooth non-convex problems.
K-means fails in high dimensions with noise and few samples.
problem Clustering in high-dimensional data with noise and limited samples.
method Simple Gaussian Mixture Model (GMM) analysis.
result Almost every partition becomes a fixed point of k-means in high dimensions.
We propose a deep neural network framework for computing prices and deltas of American options in high dimensions. The architecture of the framework is a sequence of neural networks, where each network learns the difference of the price functions between adjacent timesteps. We introduce the least squares residual of th…
Density mode clustering is a nonparametric clustering method. The clusters are the basins of attraction of the modes of a density estimator. We study the risk of mode-based clustering. We show that the clustering risk over the cluster cores --- the regions where the density is high --- is very small even in high dimens…
Minimal simplicial complexes in high dimensions always contain complex links.
problem Existence of complex links in high-dimensional embeddings.
method Demonstrated through minimal simplicial complexes in R2n. result Minimal simplicial n-complexes inevitably contain a nonsplittable two-component link. Eigenfunction maxima inside high-d nodal domains.
problem Understanding eigenfunction maxima in high-dimensional nodal domains.
method Proving eigenfunction maxima inside nodal domains of high-dimensional manifolds.
result Eigenfunction maxima are within a specific radius of the eigenvalue and dimension.
A method for clustering small datasets in high dimensions using random projections.
problem Challenges in clustering small datasets in high-dimensional spaces.
method Random projection followed by binary clustering in one-dimensional space.
result Statistically significant clustering structures can be found with as few as 100-200 points.
We consider the performance of the bootstrap in high-dimensions for the setting of linear regression, where p<n but p/n is not close to zero. We consider ordinary least-squares as well as robust regression methods and adopt a minimalist performance requirement: can the bootstrap give us good confidence intervals fo…
This paper studies robust estimation methods in high dimensions, comparing model-averaged and composite quantile estimators.
problem Understanding robustness in high-dimensional regularized estimation.
method Optimal weights are determined by minimizing the asymptotic mean squared error, incorporating regularization effects without perfect selection.
result Model-averaged and composite quantile estimators often outperform least-squares methods in prediction quality.
New approach removes data influence in high dimensions with single step.
problem Efficiently removing data influence in high-dimensional settings with strong convexity and smoothness assumptions.
method Introduces ε-Gaussian certifiability and analyzes Newton method performance.
result Single Newton step followed by Gaussian noise achieves privacy and accuracy.
New method for causal discovery in high dimensions with confounder blanket assumption.
problem Inferring causal relationships from observational data in high dimensions.
method Relaxes parametric restrictions and sparsity constraints, focusing on confounder blanket.
result Provable sound and complete structure learning algorithm with finite sample error control.
Proposes a stratified sampling method for high-dimensional models using neural active manifolds.
problem Uncertainty propagation in computationally expensive models with many inputs.
method Neural active manifolds for nonlinear dimensionality reduction, followed by stratification in the reduced space.
result Effective variance reduction in high-dimensional models using stratified sampling.
The paper develops a test for EU portfolio efficiency in high dimensions.
problem Testing the efficiency of the EU portfolio in high-dimensional settings.
method Shrinkage-based approach for portfolio weights and random matrix theory.
result Asymptotic behavior of the test statistic under high-dimensional conditions.
Improved CRT for sparse logistic regression in high dimensions.
problem Accurate inference in high-dimensional sparse logistic regression.
method Variable-distillation and decorrelation steps in CRT-logit.
result CRT-logit provides a more powerful solution with theoretical guarantees.
Improved stochastic gradient estimation for deep learning in high dimensions.
problem Inadmissibility of mini-batch gradients in high-dimensional settings.
method Stein-rule shrinkage applied to gradient computation.
result The proposed SR-Adam outperforms Adam in large-batch settings.
Strict convexity proven for certain self-expanders in high dimensions.
problem Convexity of self-expanders in mean curvature flow.
method Investigation of convexity properties for asymptotically conical self-expanders.
result Strict convexity proven for n-dimensional self-expanders. Uniqueness proven for cylindrical tangent cones in high dimensions.
problem Proving uniqueness of cylindrical tangent cones in high dimensions.
method Analyzing area-minimizing hypersurfaces in R^9.
result Uniqueness of cylindrical tangent cones Cp,qimesR in R9. Unbiased methods for alpha-divergence minimization struggle in high dimensions.
problem The difficulty of unbiased alpha-divergence minimization in high dimensions.
method Signal-to-Noise Ratio (SNR) analysis of gradient estimators.
result The SNR of the gradient estimator worsens exponentially with dimensionality.
Sliced kernelized Stein discrepancy improves goodness-of-fit tests and model learning in high dimensions.
problem The curse-of-dimensionality in kernelized Stein discrepancy (KSD).
method Sliced Stein discrepancy and its scalable variants using optimal one-dimensional projections.
result Significantly outperforms KSD and baselines in goodness-of-fit tests and improves model learning.
Paper finds a non-existence theorem for certain translators in high dimensions.
problem Non-existence of certain translators in high-dimensional spaces.
method Developed a non-existence theorem and found an example of a translator.
result Non-existence of entire Qn−1-translators in Rn+1. SignSGD analysis quantifies its effects in high dimensions.
problem Understanding signSGD's effects in high-dimensional settings.
method High-dimensional analysis of signSGD, deriving SDE and ODE for risk.
result Quantification of signSGD's effects: effective learning rate, noise compression, diagonal preconditioning, gradient noise reshaping.
The versatility of exponential families, along with their attendant convexity properties, make them a popular and effective statistical model. A central issue is learning these models in high-dimensions, such as when there is some sparsity pattern of the optimal parameter. This work characterizes a certain strong conve…