archive
Every paper Pith has read. Search by title, abstract, or pith.
883 papers in math.ST · page 1
-
SHK flow perturbations give dimension-free DP bounds
On the Stability of Spherical Hellinger-Kantorovich Flows and Their Implications for Differential Privacy
-
Muon dynamics dissipate Hamiltonian energy monotonically
Move on Muon : A Hamiltonian probability gradient flow perspective of Muon optimizer
-
The paper derives entrywise error bounds for spectral ranking in the Bradley-Terry-Luce…
Entrywise Error Bounds for Spectral Ranking with Semi-Random Adversaries
-
Fluid antennas with diffusion models hide targets from sensing
Diffusion Fluid Antenna Systems for Resilient ISAC
-
Sparse activations split scaling laws into two exponents
Asymmetric Scaling Laws from Sparse Features
-
Moment approximation detects changes in heavy-tailed data
Generalized Stochastic Approximation of the Log-Likelihood Ratio for Robust Sequential Change-Point Detection
-
Adaptive allocation matches oracle rate for multi-judge LLM scoring
Instance-Optimal Estimation with Multiple LLM Judges on a Budget
-
Entropy testing needs fewer samples than closeness testing
Entropy Equivalence Testing
-
Dead time imposes provable limits on event detection accuracy
Fundamental Bounds and Efficient Estimation for Dead-Time-Constrained Event Detection, with Application to Single-Photon Lidar
-
Gradient descent recovers true similarity metric from triplets
Operationalizing Individual Fairness via Gradient Descent and Bradley-Terry Models
-
Diffusion denoising score matching keeps bounds stable as modes separate
Diffusion-based Denoising Beats Vanilla Score Matching in Parameter Estimation: A Theoretical Explanation
-
Kernel density gradients yield conservative drifting at rate N^{-1/(d+4)}
Finite-Particle Convergence Rates for Conservative and Non-Conservative Drifting Models
-
Stronger backdoor triggers can raise clean accuracy in high dimensions
When Stronger Triggers Backfire: A High-Dimensional Theory of Backdoor Attacks
5 Piths -
Reassortant H5N1 lineages predict higher Canadian wildlife detections
Spatiotemporal dynamics and ecological risk factors of highly pathogenic avian influenza A(H5N1) in Canadian wildlife: A One Health surveillance analysis
-
Point clouds recover de Rham cohomology and Pontryagin numbers
Empirical Hodge Laplacians, Cohomology Ring, and Manifold Learning
-
Circular Chatterjee coefficient stays zero under independence
A Circular Chatterjee's Correlation Coefficient
-
Infinite proposal limit yields new MCMC algorithms
Mad Props: Parallelism in Markov Chain Monte Carlo Through the Lens of the Infinite Proposal Limit
-
Optimal mean estimators must have sensitivity Omega(eta + sqrt(eta d/n))
Robust Statistical Estimators with Bounded Empirical Sensitivity
-
DDEVD derives optimal bandwidth from explicit MISE
Data driven extreme value distribution estimation: Derivation of the Mean Integrated Squared Error, optimal bandwidth selection and stability conditions
-
L2 over Wasserstein gives random measures Riemannian geometry
$L^2$ over Wasserstein: Statistical Analysis for Optimal Transport
-
Mixed test characterizes adaptive separation rates in sparse functional testing
Linear Functional Testing with General Loadings in Sparse Regression: Separation Rates and Computational Barriers
-
Maximizing naive bounds recovers misspecified Cramér-Rao bound
Revisiting the Misspecified Cram\'er-Rao Bound
-
Localization method builds Transformers from local kernels
The General Theory of Localization Methods
-
Smoothing with auxiliary sample gives regression confidence regions
New Confidence Regions for Linear Regression Parameters with Stationary-Ergodic Dependent Errors
-
Interval-length sampling minimizes worst-case error for bounded totals
Minimax unbiased estimation for finite populations with bounded outcomes
-
AMISE formula holds for densities with Lipschitz first derivatives
Kernel Density Estimation under $C^{1,1}$ Regularity: AMISE, Weak Curvature, and Plug-in Bandwidths
-
MSE bounds derived for expected signature from dependent paths
Finite-Sample Bounds for Expected Signature Estimation under Weak Dependence
-
Graph topology decides when models collapse
When Does Model Collapse Occur in Structured Interactive Learning?
-
Complete-case beats weighting in federated missing-data studies
Federated Learning with Incomplete Data: When to Use Complete Cases and When to Weight
-
Goodness-of-fit test for IC models works without pre-whitening
A Goodness-of-Fit Test for Independent Component Models in High Dimensions
-
Bounds separate Monte Carlo and proposal errors in data-driven importance sampling
Error Bounds for Importance Sampling with Estimated Proposal Distributions
-
Pairwise distances give exact formula for average projection discrepancy
Uniform projection designs under the stratified $L_2$-discrepancy
-
SNR=1 sets exact threshold for multi-view spike recovery
Sharp Spectral Thresholds for Multi-View Spiked Wigner Models
-
Set-valued policies output treatment sets instead of singles
Set-Valued Policy Learning
-
Privacy budget sets floor on federated estimation error
General Lower Bounds for Differentially Private Federated Learning with Arbitrary Public-Transcript Interactions
2 Piths -
Variance-aware regret bound proven optimal for logistic MDPs
Minimax Optimal Variance-Aware Regret Bounds for Multinomial Logistic MDPs
-
Influence bounds monotone hypercube estimation to K/sqrt(log n)
Influence as soft sparsity: Estimation of monotone functions on $\{0,1\}^d$
-
Spectral algorithms hit optimal thresholds in two-view models
Optimal Spectral Algorithms for Correlated Two-view Models in High Dimensions
-
Factor-augmented SGD converges with streaming high-dimensional data
Factor Augmented High-Dimensional SGD
-
Inference functionals give consistency for models without densities
Inference Functionals and Observation Operators for Distributional Statistical Models
-
Spatial Cramér-von Mises test extended to β-mixing fields
The Spatial Cram'{e}r--von Mises Test of Independence under $\beta$-Mixing: Asymptotic Theory and Python Implementation
-
Kernels from scores characterize four stochastic orders
Kernel Characterisations of Stochastic Orders Within Parametric Density Families
-
Pointwise feature eigenvalues give tight DNN generalization bounds
Pointwise Generalization in Deep Neural Networks
-
Empirical power-kernel MMD decays as N^(-1/2(1+q/β))
Sharp Rates of MMD Empirical Estimation with Power Kernels
-
Overestimating factors by a fixed amount keeps PCA consistent
Fixed-order PCA: Theory for Overestimated Factor Models
-
Infinite-dimensional GAN learns invariant distribution from single deterministic orbit
Generative Adversarial Learning from Deterministic Processes
-
Riesz basis yields closed-form ANOVA for dependent inputs
Generalized Functional ANOVA in Closed-Form: A Unified View of Additive Explanations
-
Quantile error in heavy-tailed projections splits into three parts
On Stability and Decomposition of Sample Quantiles under Heavy-Tailed Distributions
-
Heavy-tailed quantiles split into direction shift
On Stability and Decomposition of Sample Quantiles under Heavy-Tailed Distributions
-
Consistent hitting-time estimators for Markov chains from transition rates
Multi-state model with temporal-consistent survival analysis for homogeneous Markov chains