Stochastic gradient ascent with averaging learns Lagrangian multipliers for MILP at the minimax rate Θ(s/√N) and faster Θ(s/N) for warm-start, closing the gap between upper and lower bounds.
Introduction to Nonparametric Estimation , pages=
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
Empirical Bernstein calibrated confidence intervals achieve nominal coverage up to small remainders and minimax-optimal widths for nonparametric regression and density estimation under local smoothness assumptions.
A grid-sketching technique enables ε-accurate estimation of W₂² between α-Hölder smooth distributions on (0,1)^d in time ε^{-max(2, (d+1+o(1))/(1+α))}.
Causal effects are identifiable for categorical unobserved confounders via mixture learning and tensor decomposition, yielding consistent estimators with non-asymptotic guarantees.
Multiscale CMH scanning generalizes the classic test to continuous spaces, achieving consistency for conditional independence testing by conditioning on marginal order statistics without requiring large stratum sizes.
citing papers explorer
-
Provably Data-driven Lagrangian Relaxation for Mixed Integer Linear Programming
Stochastic gradient ascent with averaging learns Lagrangian multipliers for MILP at the minimax rate Θ(s/√N) and faster Θ(s/N) for warm-start, closing the gap between upper and lower bounds.
-
Safe and Sharp Honest Inference for Nonparametric Estimation via Empirical Bernstein Calibration
Empirical Bernstein calibrated confidence intervals achieve nominal coverage up to small remainders and minimax-optimal widths for nonparametric regression and density estimation under local smoothness assumptions.
-
Optimizing Computational-Statistical Runtime for Wasserstein Distance Estimation
A grid-sketching technique enables ε-accurate estimation of W₂² between α-Hölder smooth distributions on (0,1)^d in time ε^{-max(2, (d+1+o(1))/(1+α))}.
-
Causal Inference with Categorical Unobserved Confounder via Mixture Learning
Causal effects are identifiable for categorical unobserved confounders via mixture learning and tensor decomposition, yielding consistent estimators with non-asymptotic guarantees.
-
Multiscale Cochran-Mantel-Haenszel Scanning for Conditional Dependency
Multiscale CMH scanning generalizes the classic test to continuous spaces, achieving consistency for conditional independence testing by conditioning on marginal order statistics without requiring large stratum sizes.