{"total":22,"items":[{"citing_arxiv_id":"2606.25797","ref_index":60,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Confidence Sequences for Online Statistical Model Checking of Markov Decision Processes","primary_cat":"cs.AI","submitted_at":"2026-06-24T13:16:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Introduces and implements confidence sequences for online statistical model checking of MDPs that require 50x fewer samples than prior state-of-the-art union-bound approaches.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.22008","ref_index":60,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"An Optimal Transportation Approach for Improved Confidence Intervals","primary_cat":"stat.ME","submitted_at":"2026-06-20T12:15:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"An optimal transport method is proposed to construct confidence intervals with improved coverage, including theoretical consistency results, error bounds, and simulation comparisons.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.20427","ref_index":3,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Private Rate-Double-Robust Inference","primary_cat":"math.ST","submitted_at":"2026-06-18T16:08:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":8.0,"formal_verification":"none","one_line_summary":"Local privacy mechanisms preserve rate-double-robustness, enabling unbiased and semiparametrically efficient inference on target parameters indexed linearly by infinite-dimensional and nonlinearly by low-dimensional components from noisy private data.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":", 2019) or homomorphic encryption ( Gentry, 2009; Y ang et al., 2019). 3 Each functional χ : PV X ! R yields a parameter χ(PV X ). Section 3.1 introduces our class of χ which yield rate-double-robust parameters; Section 3.2 studies their inferential properties. Notation. For h : V \u0002 X ! R, we let PV X h := PV X h(V, X ) := R V×X h(v, x) dPV X (v, x). Fix p 2 [1, 1). With khkLp(PV X ) := ( PV X jhjp) 1 p , write Lp(PV X ) for all h : V \u0002 X ! R with khkp Lp(PV X ) < 1, and L0 p(PV X ) for all h 2 Lp(PV X ) with PV X h = 0 . Let khk∞ := sup(v,x)∈V×X jh(v, x)j, and ρ((h, a), (h′, a′)) := kh h′kL2(PV X ) + ja a′j be a metric on L2(PV X ) \u0002 R 3 (h, a). Let δ(v,x) be the Dirac measure at (v, x) 2 V \u0002 X. We call a (π1\u000eV, π2\u000eV, . . .) a collection of coordinates of V , if all the πj \u000ev 2 Vj′ for all v 2 V for some Vj′ 2 fV1, V2, . . .g; for example, if V = V1 \u0002 V2 \u0002 V3 with corresponding V = (V1, V2, V3), then (V2, V1) is a collection of coordinates of V . 3.1. Rate-Double-Robust Parameter Class Let V1 and V2 be two arbitrary collections of coordinates of V with values in V1 and V2, respectively , where, importantly , V2 is finite. For given m, g : V \u0002 X ! R, define the regressions µX (v1, x) := E [ m(V, X ) j V1 = v1, X = x] , (v1, x) 2 V1 \u0002 X, γV(v2) := E [ g(V, X ) j V2 = v2] , v 2 2 V2, (R) assuming µX 2 L2(PV1X), γV 2 L2(PV2). For a given f : V \u0002 X \u0002 L2(PV1X) \u0002 L2(PV2) ! R, our targets are χ(PV X ) = Ef (V, X, µX , γV). As V2 is finite, we can define without loss of generality our target parameter as χ(PV X ) := Ef (V, X, µX , γV(c)) (T) for a fixed c 2 V2, and f : V \u0002 X \u0002 L2(PV1X) \u0002 Γ !"},{"citing_arxiv_id":"2606.17319","ref_index":34,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Tight $L_\\infty$ Sample Complexity for Low-Degree and Sparse Boolean Polynomials","primary_cat":"stat.ML","submitted_at":"2026-06-15T22:00:03+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Minimax sample complexity for uniform L_infty estimation is Theta(n^{d+1}) for degree-d polynomials and Theta(ns^2) for s-sparse Fourier-Walsh polynomials under noise, exceeding noiseless rates by factors of n and s.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.15464","ref_index":43,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Certified Finite-Shot Operating Windows for Virtual Distillation and Symmetry Verification","primary_cat":"quant-ph","submitted_at":"2026-06-13T20:42:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Proves finite-shot mean-squared-error laws for virtual distillation and symmetry verification that define certified operating windows and a selection trichotomy for their comparison.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.00414","ref_index":21,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Auditing Near-Optimal Policies Can Be Exponentially Hard: Conditional Query Lower Bounds via Occupancy Rashomon Capacity","primary_cat":"cs.LG","submitted_at":"2026-05-29T23:09:01+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Conditional lower bounds prove that exact local-query auditing of near-optimal policies requires Ω(2^{Hopt^F(ε)}) queries when occupancy Rashomon capacity is realized by a sparse-signature packing.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.28251","ref_index":40,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Counterfactually Fair Regression via Optimal Transport","primary_cat":"stat.ML","submitted_at":"2026-05-27T10:00:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Derives closed-form optimal counterfactually fair regressor via barycentric quantile map and proves Õ(n^{-1/3}) finite-sample fairness and risk bounds for discretized post-processing under mild assumptions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.19989","ref_index":258,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Error Bounds for Importance Sampling with Estimated Proposal Distributions","primary_cat":"math.ST","submitted_at":"2026-05-19T15:27:17+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Derives non-asymptotic error bounds for standard, defensive, and self-normalized importance sampling with random KDE proposals from geometrically ergodic Markov chains, separating n^{-1/2} Monte Carlo error from MIAE/MISE proposal error.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18042","ref_index":93,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"On efficient robust regression with subquadratic samples","primary_cat":"cs.DS","submitted_at":"2026-05-18T08:34:07+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Near-linear time algorithm for robust regression under Gaussian covariates achieves O(sqrt(ε κ)) error with Õ(d/ε⁴) samples when ε κ ≲ 1, plus SQ and low-degree lower bounds.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11238","ref_index":35,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Efficient Robust Constrained Signal Detection via Kolmogorov Width Approximations","primary_cat":"math.ST","submitted_at":"2026-05-11T20:56:17+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Polynomial-time SDP and ellipsoid-based approximation of Kolmogorov widths yields efficient robust detection boundaries matching upper bounds up to polylog factors for structured constrained signals.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.08672","ref_index":7,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Posterior Concentration of Bayesian Physics-Informed Neural Networks for Elliptic PDEs","primary_cat":"math.ST","submitted_at":"2026-05-09T04:19:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Bayesian PINNs for elliptic PDEs have posteriors that contract around the true solution at near-optimal rates, with the prior adapting automatically to unknown smoothness.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.07483","ref_index":5,"ref_count":2,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Does Your Neural Network Extrapolate? Feature Engineering as Identifiability Bias for OOD Generalization","primary_cat":"cs.LG","submitted_at":"2026-05-08T09:25:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Out-of-distribution extrapolation is non-identifiable from in-distribution data alone; the feature map, label map, and model class supply the identifiability bias that determines whether a network succeeds or fails at OOD generalization.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.05458","ref_index":72,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Model Form Identification in High-Dimensional Functional Linear Regressions","primary_cat":"stat.ME","submitted_at":"2026-05-06T21:33:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MoFI-FLR recovers active covariates and identifies their true functional forms (simple or complex) in high-dimensional functional linear regressions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.03781","ref_index":80,"ref_count":2,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Safe and Sharp Honest Inference for Nonparametric Estimation via Empirical Bernstein Calibration","primary_cat":"math.ST","submitted_at":"2026-05-05T14:08:27+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.01775","ref_index":120,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"A Semi-Supervised Kernel Two-Sample Test","primary_cat":"stat.ML","submitted_at":"2026-05-03T08:26:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A semi-supervised kernel two-sample test integrates unlabeled covariate data to achieve asymptotic normality under the null, higher power than standard kernel tests, and consistency against fixed and local alternatives.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.25668","ref_index":19,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Sharp adaptive nonparametric testing for constant volatility","primary_cat":"math.ST","submitted_at":"2026-04-28T14:02:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Constructs a minimax-optimal adaptive test for constant volatility in the nonparametric Gaussian white noise model under infill asymptotics, measuring deviations via the ratio of sigma(t) to its L2-average.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.25368","ref_index":27,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Self-organized regime switching in null-recurrent dynamics","primary_cat":"math.ST","submitted_at":"2026-04-28T08:33:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Profile MLE for the regime-switching threshold in null-recurrent diffusion converges at rate n^{-(1+γ)/2} to the arg sup of a doubly stochastic drifted Poisson process involving local time of oscillating Brownian motion.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.10398","ref_index":22,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Estimating heterogeneous treatment effects with survival outcomes via a deep survival learner","primary_cat":"stat.ME","submitted_at":"2026-04-12T01:11:44+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DSL uses doubly robust pseudo-outcomes and a multi-output neural network to jointly estimate time-varying conditional average treatment effects for right-censored survival data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2512.03021","ref_index":4,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Semiparametric Robust Estimation of Population Location","primary_cat":"stat.CO","submitted_at":"2025-12-02T18:48:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A semiparametric robust estimator for population location models the dominant component parametrically and the background nonparametrically, with FFT acceleration for scalable likelihood maximization.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2505.16329","ref_index":23,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"High-Dimensional Private Linear Regression with Optimal Rates","primary_cat":"stat.ML","submitted_at":"2025-05-22T07:34:27+00:00","verdict":"ACCEPT","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"DP-GD achieves minimax optimal non-asymptotic risk O(γ + γ²/ρ²) for well-conditioned high-dimensional data and power-law scaling for ill-conditioned power-law spectra, with the exponent depending on the privacy parameter ρ.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2410.16477","ref_index":2,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Finite-Sample and Distribution-Free Fair Classification: Optimal Trade-off Between Excess Risk and Fairness, and the Cost of Group-Blindness","primary_cat":"stat.ME","submitted_at":"2024-10-21T20:04:17+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A post-processing algorithm achieves distribution-free finite-sample group fairness guarantees with controlled excess risk for both group-aware and group-blind settings, shown minimax-optimal up to logs via lower bound.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2303.03237","ref_index":8,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Convergence Rates for Non-Log-Concave Sampling and Log-Partition Estimation","primary_cat":"stat.ML","submitted_at":"2023-03-06T15:53:44+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Optimal rates for non-log-concave sampling and log-partition estimation are sometimes equal to or faster than optimization rates, but polynomial-time algorithms fall short of near-optimal performance.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}