ℓ₂-Boosting exhibits benign overfitting with logarithmic excess variance decay Θ(σ²/log(p/n)) under isotropic noise due to ℓ₁ bias, and a subdifferential early stopping rule recovers minimax-optimal ℓ₁ rates.
hub
Journal of the Royal Statistical Society Series B: Statistical Methodology , volume=
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
hub tools
citation-role summary
background 3
citation-polarity summary
years
2026 12verdicts
UNVERDICTED 12roles
background 3representative citing papers
Derives ODE limits of Adam-DA showing that first- and second-order momentum parameters reverse their convergence roles in zero-sum games compared to minimization, validated on GAN experiments.
Semi-discrete Flow Matching produces terminal assignment regions that are topologically simple (open, simply connected, homeomorphic to the ball under assumption) yet geometrically distinct from optimal transport Laguerre cells, as they can be non-convex with curved boundaries.
RAIC unifies uniform recovery of structured signals from nonlinear observations via PGD, yielding error rates comparable to nonuniform guarantees up to log factors in sparse and 1-bit settings.
PRADAS derives a Bayes-optimal mirror statistic for any splitting scheme, establishes asymptotic FDR control under weak dependence, and optimizes the split ratio as a stopping time to improve power over standard equal-split methods.
AGESS combines elliptical slice sampling with diminishing adaptation to self-correct to fast mixing while preserving ergodicity for non-elliptical, multi-modal, and high-dimensional targets.
spBART extends BART by modeling low-dimensional covariates parametrically for interpretability and high-dimensional epigenetic predictors nonparametrically, with a CV-based variable selection procedure, achieving AUC 0.96 on multiple myeloma epigenetic data.
An augmented kernel ridge regression estimator separates linear and nonlinear components to achieve sharp oracle inequalities and minimax optimal prediction risk under general kernels.
A calibration procedure yields a weighted transported average treatment effect with asymptotically valid and efficient inference when experimental data grows slower than observational data, even without positivity or correct OLS specification.
A novel spatially dependent shrinkage prior for Poisson regression improves region selection and prediction accuracy for count data with spatially correlated covariates.
CAFE assesses the fit of observational CATE estimates by partitioning RCT data via propensity scores and comparing to experimental group averages, with theory and extensions for confounders.
SABRE is a simulation-based bias correction framework that reduces finite-sample bias for the parametric component and dispersion parameter in semiparametric regression models, with asymptotic bias reduction without variance inflation shown for generalized partially linear models.
citing papers explorer
-
When Does $\ell_2$-Boosting Overfit Benignly? High-Dimensional Risk Asymptotics and the $\ell_1$ Implicit Bias
ℓ₂-Boosting exhibits benign overfitting with logarithmic excess variance decay Θ(σ²/log(p/n)) under isotropic noise due to ℓ₁ bias, and a subdifferential early stopping rule recovers minimax-optimal ℓ₁ rates.
-
Understanding Dynamics of Adam in Zero-Sum Games: An ODE Approach
Derives ODE limits of Adam-DA showing that first- and second-order momentum parameters reverse their convergence roles in zero-sum games compared to minimization, validated on GAN experiments.
-
Tessellations of Semi-Discrete Flow Matching
Semi-discrete Flow Matching produces terminal assignment regions that are topologically simple (open, simply connected, homeomorphic to the ball under assumption) yet geometrically distinct from optimal transport Laguerre cells, as they can be non-convex with curved boundaries.
-
Robust Uniform Recovery of Structured Signals from Nonlinear Observations
RAIC unifies uniform recovery of structured signals from nonlinear observations via PGD, yielding error rates comparable to nonuniform guarantees up to log factors in sparse and 1-bit settings.
-
PRADAS: PRior-Assisted DAta Splitting for False Discovery Rate Control
PRADAS derives a Bayes-optimal mirror statistic for any splitting scheme, establishes asymptotic FDR control under weak dependence, and optimizes the split ratio as a stopping time to improve power over standard equal-split methods.
-
Adaptive Generalized Elliptical Slice Sampling
AGESS combines elliptical slice sampling with diminishing adaptation to self-correct to fast mixing while preserving ergodicity for non-elliptical, multi-modal, and high-dimensional targets.
-
Semi-Parametric Bayesian Additive Regression Trees for Risk Prediction with High-Dimensional Epigenetic Signatures and Low-Dimensional Covariates
spBART extends BART by modeling low-dimensional covariates parametrically for interpretability and high-dimensional epigenetic predictors nonparametrically, with a CV-based variable selection procedure, achieving AUC 0.96 on multiple myeloma epigenetic data.
-
Adaptive Kernel Ridge Regression with Linear Structure: Sharp Oracle Inequalities and Minimax Optimality
An augmented kernel ridge regression estimator separates linear and nonlinear components to achieve sharp oracle inequalities and minimax optimal prediction risk under general kernels.
-
Transporting treatment effects by calibrating large-scale observational outcomes
A calibration procedure yields a weighted transported average treatment effect with asymptotically valid and efficient inference when experimental data grows slower than observational data, even without positivity or correct OLS specification.
-
Bayesian Region Selection and Prediction in Poisson Regression with Spatially Dependent Global-Local Shrinkage Prior
A novel spatially dependent shrinkage prior for Poisson regression improves region selection and prediction accuracy for count data with spatially correlated covariates.
-
Assessing Estimate of CATE from Observational Data via an RCT Study
CAFE assesses the fit of observational CATE estimates by partitioning RCT data via propensity scores and comparing to experimental group averages, with theory and extensions for confounders.
-
Bias Correction for Semiparametric Regression Models
SABRE is a simulation-based bias correction framework that reduces finite-sample bias for the parametric component and dispersion parameter in semiparametric regression models, with asymptotic bias reduction without variance inflation shown for generalized partially linear models.