archive
Every paper Pith has read. Search by title, abstract, or pith.
355 papers in stat.TH · page 1
-
Valiant learnability equals poly-size query compression
What is Learnable in Valiant's Theory of the Learnable?
-
Pattern frequencies in rank plots obey a functional CLT
Pattern-based tests for two-dimensional copulas
-
Weighted tail estimators work for any censoring strength
Weighted and Truncated Tail Index Estimation under Random Censoring: A Unified Full-Range Framework
-
Markov product extends Chatterjee's correlation to dependence functions
Dependence functions based on Chatterjee's rank correlation
-
Learned continuous perturbations boost LLM extrapolation to new domains
Learning Perturbations to Extrapolate Your LLM
-
Change-point sample needs depend on both jumps and positions
The Sample Complexity of Multiple Change Point Identification under Bandit Feedback
-
Sampler matches smooth-case rate for composite log-concave densities
A proximal gradient algorithm for composite log-concave sampling
-
Bootstrap yields valid CIs for offline RL value functions
Model-based Bootstrap of Controlled Markov Chains
-
Monotone operators approximated via graph convergence
Approximation of Maximally Monotone Operators : A Graph Convergence Perspective
-
Pattern tests for independence get explicit null limits
Efficiency of pattern-based independence test
-
Weaker likelihood ratio shapes still give stochastic orders
Stochastic Ordering under Weaker Likelihood-Ratio Shape Conditions
-
Augmented KRR separates linear and nonlinear parts
Adaptive Kernel Ridge Regression with Linear Structure: Sharp Oracle Inequalities and Minimax Optimality
-
Bayesian bootstrap recovers Efron method as special case
Bayesian and Empirical Bayesian Bootstrapping
-
Sparse Bayesian KANs achieve near-minimax contraction
Posterior Contraction Rates for Sparse Kolmogorov-Arnold Networks in Anisotropic Besov Spaces
-
MLP scales small-ensemble covariances to cut EnKF error
Machine Learning-Based Covariance Correction for Ensemble Kalman Filter with Limited Ensemble Size
-
McDiarmid bound removes K-scaling barrier in streaming decision trees
MIST: Reliable Streaming Decision Trees for Online Class-Incremental Learning via McDiarmid Bound
-
Gaussian limits for spectral statistics survive fourth-moment corrections
The Geometry of Spectral Fluctuations: On Near-Optimal Conditions for Universal Gaussian CLTs, with Statistical Applications
-
Deterministic residual update removes stochastic variance in ensemble filters
A Data-Consistent Approach to Ensemble Filtering
-
The paper develops a polynomial-time algorithm using semidefinite programming relaxation…
Efficient Robust Constrained Signal Detection via Kolmogorov Width Approximations
-
Stable barcodes track how dependency clusters evolve in dynamic Bayesian networks
A Stable Distance Persistence Homology for Dynamic Bayesian Network Clustering
-
Even-order GW functionals converge at rate n^{-2/max{min(d,4)}}
Empirical Convergence of Even-Order Gromov-Wasserstein Functionals
-
Bahadur representation yields high quantile homogeneity test
A Generative High Quantile Homogeneity Test Using Bahadur Representation for Heteroskedastic High Quantile Regression of Tail Dependent Time Series
-
Modularity shows overlap gap on stochastic block model
The stochastic block model has the overlap graph property for modularity
-
Moments made orthogonal to any order with fixed extra parameters
Higher-Order Neyman Orthogonality in Moment-Condition Models
-
Finite VC dimension enables finite-sample tests for distribution trade-offs
When Are Trade-Off Functions Testable from Finite Samples?
-
LASSO matches homogeneous threshold for mixed-quality sparse data
Price of Quality: Sufficient Conditions for Sparse Recovery using Mixed-Quality Data
-
Closed-form spectral formulas estimate density ratios from moments
A Spectral Framework for Closed-Form Relative Density Estimation
-
Infinite measures admit unique cyclically monotone zero-couplings
Zero-couplings of infinite measures with cyclically monotone support and multivariate regular variation
-
New measure tracks tail dependence in heavy-tailed linear processes
Measuring Tail Dependence in Linear Processes: Theory and Empirics
-
Test error in augmented random features depends only on data and augmentation moments
Characterizing the Generalization Error of Random Feature Regression with Arbitrary Data-Augmentation
-
Gaussian priors hit minimax rates for point-process intensity
Increasing domain asymptotics for covariate-based nonparametric Bayesian intensity estimation with Gaussian and Besov-Laplace priors
-
GAN method estimates full causal distributions with minimax optimality
Extended Wasserstein-GAN Approach to Causal Distribution Learning: Density-Free Estimation and Minimax Optimality
-
Tests for exposure mapping models cannot beat random rejection
On the Impossibility of Specification Testing of Interference Models Based on Exposure Mappings
-
Normalizing flows recover fast equilibrium from slow data alone
Learning stochastic multiscale models through normalizing flows
-
Regularization scheme extends to conditional density estimation
The general regularisation scheme applied to conditional density estimation
-
Exact signal thresholds derived for submatrix detection
Minimax optimal submatrix detection: Sharp non-asymptotic rates
-
Multi-source transfer carries adaptation cost past phase transition
The Statistical Cost of Adaptation in Multi-Source Transfer Learning
-
Bridge functions identify path-specific effects with hidden confounders
Proximal Path-Specific Inference
-
Feature selection tolerates noise and weak symmetry
Universal Feature Selection with Noisy Observations and Weak Symmetry Conditions
-
Forward KL regularization yields first fast rates for offline contextual bandits
Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability
-
Smoothed Wasserstein costs converge at moment-based rates
Two-Sample Inference for Gaussian-Smoothed Wasserstein Costs with Finite Moments
-
Online EM inherits batch CLT with small tracking lag
Higher-Order Equilibrium Tracking for EM-Compressible Online Estimation
-
Estimators achieve minimax optimal rates for unbalanced transport-growth pairs
Minimax Optimal Estimation of Transport-Growth Pairs in Unbalanced Optimal Transport
-
Framework links algorithm outputs to MLE for latent space networks
Bridging Theory and Practice: Statistical Inference for Latent Space Models of Networks
-
Bayesian PINNs contract to PDE solutions at near-minimax rates
Posterior Concentration of Bayesian Physics-Informed Neural Networks for Elliptic PDEs
-
Nonparametric EB intervals reach nominal coverage asymptotically
Nonparametric Empirical Bayes Confidence Intervals
-
Attention selectivity emerges at scale n^{2/(d-1)}
Scaling Limits of Long-Context Transformers
-
Sinkhorn divergence tests full distributional treatment effects
Sinkhorn Treatment Effects: A Causal Optimal Transport Measure
-
LRT asymptotics stay sup of bar-chi process with unidentifiable nuisance
Asymptotics for likelihood ratio tests of boundary points with singular information and unidentifiable nuisance parameters
-
Boundary LRTs converge to supremum of bar-chi-squared process
Asymptotics for likelihood ratio tests of boundary points with singular information and unidentifiable nuisance parameters