FHDMs achieve minimax optimal TV convergence rates for spherically supported Sobolev data distributions up to log factors, the first optimality result for random-time denoising diffusion models.
users are more active than others and popular items are rated more frequently
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
GL-LowPopArt is a Catoni-style two-stage estimator for generalized low-rank trace regression that attains state-of-the-art bounds and nearly instance-wise minimax optimality up to the Hessian condition number.
Introduces the MCB estimator for pointwise Wasserstein barycenter quantile estimation under sparse sampling by modeling the distribution of latent unit-level quantiles via marginal CDF distributions estimated with binomial mixtures, with consistency and asymptotic normality.
Proves reverse Poincaré inequality on global attractor of 2D reaction-diffusion system to obtain near-parametric statistical recovery of initial conditions from discrete observations.
citing papers explorer
-
Statistical Convergence of Spherical First Hitting Diffusion Models
FHDMs achieve minimax optimal TV convergence rates for spherically supported Sobolev data distributions up to log factors, the first optimality result for random-time denoising diffusion models.
-
GL-LowPopArt: A Nearly Instance-Wise Minimax-Optimal Estimator for Generalized Low-Rank Trace Regression
GL-LowPopArt is a Catoni-style two-stage estimator for generalized low-rank trace regression that attains state-of-the-art bounds and nearly instance-wise minimax optimality up to the Hessian condition number.
-
Estimating the Wasserstein barycenter of one-dimensional distributions under sparse sampling
Introduces the MCB estimator for pointwise Wasserstein barycenter quantile estimation under sparse sampling by modeling the distribution of latent unit-level quantiles via marginal CDF distributions estimated with binomial mixtures, with consistency and asymptotic normality.
-
On statistical inference for non-linear dynamical systems evolving in their global attractor
Proves reverse Poincaré inequality on global attractor of 2D reaction-diffusion system to obtain near-parametric statistical recovery of initial conditions from discrete observations.