archive
Every paper Pith has read. Search by title, abstract, or pith.
883 papers in math.ST · page 8
-
Half-mass radii produce valid conformal sets for any sample size
Conformal Robust Set Estimation
-
Gamma expansion yields first-passage densities for logistic harvesting
Gamma-Based Expansion for the First-Passage Time Distribution of Stochastic Logistic Models with Harvesting
-
Horospherical depth always admits a centerpoint on Hadamard manifolds
Horospherical Depth and Busemann Median on Hadamard Manifolds
-
Busemann median exists for any probability measure on Hadamard manifolds
Horospherical Depth and Busemann Median on Hadamard Manifolds
-
Resolvents approximate deterministic matrices in covariance mixtures
Spectral approximation for the separable covariance mixture model
-
Bayesian prior controls FDR in high-dimensional Gaussian graphs
A Bayesian framework with adaptive elastic nets for the inference of Gaussian graphical models
-
Quickest change detection scales to constrained multi-sensor systems
Multi-stream Quickest Change Detection: Foundations and Recent Advances
-
Wasserstein shadow projection is bi-Hölder continuous
Quantitative Stability of the Shadow for Wasserstein Projections and Sample Complexity
-
BLUE variance for stationary mean fixed by spectrum near zero
Asymptotic behavior of the variance of the BLUE for the mean of stationary processes
-
Simple removal of bad data fails to fix dynamic estimates
Subsample-Based Estimation under Dynamic Contamination
-
Subsampling breaks under dynamic contamination
Subsample-Based Estimation under Dynamic Contamination
-
Error bounds proven for replay and distillation under task dependencies
Recovery Guarantees for Continual Learning of Dependent Tasks: Memory, Data-Dependent Regularization, and Data-Dependent Weights
-
Latent intersections and complements stay recoverable from data alone
Diverse Dictionary Learning
-
Langevin AIS time complexity quadratic in inverse temperature
Convergence of Langevin AIS for multimodal distributions
-
Joint exclusivity vectors exist iff sum of survival probs at zero ≤ n-1
Joint Exclusivity
-
Low-degree testing bounds imply recovery hardness via contiguity
Algorithmic Contiguity from Low-Degree Heuristic II: Predicting Detection-Recovery Gaps
-
Bootstrap matches sampling distribution of DML estimators
Bootstrap consistency for general double/debiased machine learning estimators
-
Mixtures on low-dimensional subspaces are uniquely identifiable
Learning Mixtures of Nonparametric and Convolutional Measures on Effectively Low-dimensional Affine Spaces
-
Generalized prior extends Dirichlet process for flexible skewness
Bayesian analysis for a generalised Dirichlet process prior
-
Fibonacci concatenation may be normal if interior digits stay uniform
On the normality of the concatenated Fibonacci constant
-
Local geometry governs linear convergence rates
Trajectory-Restricted Optimization Conditions and Geometry-Aware Linear Convergence
-
Horseshoe prior matches exact minimax rates for sparse predictive inference
Horseshoe Predictive Inference
-
Strang splitting gives consistent estimates for nonlinear Pearson SDEs
Strang splitting estimator for nonlinear multivariate stochastic differential equations with Pearson-type multiplicative noise
-
Berry-Esseen bound controls covariance error for long-range series
Simultaneous Inference for Covariance and Precision Matrices of Long-Range Dependent Time Series
-
Level sets extrapolate max-stable fields with heavy Fréchet tails
Extrapolation of max-stable random fields with Fr\'echet marginals
-
Decompounding estimator on symmetric spaces matches Euclidean rates
Decompounding on Compact Symmetric Spaces
-
Weakened graph rules expand front-door causal identification
Generalization of Pearl's Front-Door Criterion
-
Orthogonal kernels decompose SVM norm across interaction orders
Structural interpretability in SVMs with truncated orthogonal polynomial kernels
-
Cloning stabilizer states requires linear samples
Cloning is as Hard as Learning for Stabilizer States
-
Order statistic inequality holds approximately under mild violations
On a Probability Inequality for Order Statistics with Applications to Bootstrap, Conformal Prediction, and more
-
Weighted extropy measures for extremes uniquely characterize distributions
On general weighted cumulative residual (past) extropy of extreme order statistics
-
Weighted residuals restore valid tests for regressions with growing predictors
Model Checking for Regressions Based on Weighted Residual Processes with Diverging Number of Predictors
-
Unified adaptive design merges screening and optimization
HASOD: A Hybrid Adaptive Screening-Optimization Design for High-Dimensional Industrial Experiments
-
-
Möbius function needs order R samples to learn
Arithmetic functions and learning theory
-
Early stopping yields optimal adaptive rates with less computation
Early-stopped aggregation: Adaptive inference with computational efficiency
-
Binary autoregressions aggregate to Poisson models under rare scaling
Generalized Autoregressive Multivariate Models: From Binary to Poisson
-
Bounds cap Pearson matrix ratio growth at 1.7 with 95% probability
Finite-Step Bounds for Iterated Correlation Matrices
-
Integer moving-average fields give closed-form count distributions
The Integer-valued Moving-Average Random Field
-
Integer moving-average fields give closed-form count models
The Integer-valued Moving-Average Random Field
-
Ordinary least squares equals one attention pass in linear transformers
Ordinary Least Squares is a Special Case of Transformer
-
The paper proposes a gradient-free dimension reduction technique for Bayesian inference…
Covariance-Informed Subspace: an Adaptive Gradient-Free Input Dimension Reduction Method for Bayesian Inference
-
Fixed center effects remove unmeasured confounding in LAGO trials
Addressing Confounding by Indication Through (Un)Measured Centre Characteristics in Learn-As-you-GO(LAGO) Trials
-
Fixed centre effects control confounding in LAGO trials
Addressing Confounding by Indication Through (Un)Measured Centre Characteristics in Learn-As-you-GO(LAGO) Trials
-
Noisy CUSUM sums detect private multi-stream changes with delay bounds
Sequential Change Detection for Multiple Data Streams with Differential Privacy
-
Degenerate Gaussian mixtures identifiable via piecewise affine mixing
Identifiability of Potentially Degenerate Gaussian Mixture Models With Piecewise Affine Mixing
-
Different f-divergence OT regularizers share solutions via cost change
Equivalence of optimal transport problems to regularization on the family of f-divergences
-
EOT plans converge in distribution for functionals including colocalization
Distributional Convergence of Empirical Entropic Optimal Transport and Statistical Applications
-
Graphical SLOPE error converges to convex SLOPE limit
Asymptotic Theory for Graphical SLOPE: Precision Estimation and Pattern Convergence
-
n^{-2} geometric correction refines estimator covariance
On Higher-Order Geometric Refinements of Classical Covariance Asymptotics: An Approach via Intrinsic and Extrinsic Information Geometry