paper-with-me

Papers

Optimal score estimation via empirical Bayes smoothing

2024-02-12 · Andre Wibisono, Yihong Wu, Kaylee Yingxi Yang

We study the problem of estimating the score function of an unknown probability distribution $\rho^*$ from $n$ independent and identically distributed observations in $d$ dimensions. Assuming that $\rho^*$ is subgaussian and has a Lipschitz-continuous score function $s^*$, we establish the optimal rate of $\tilde \Theta(n^{-\frac{2}{d+4}})$ for this estimation problem under the loss function $\|\hat s - s^*\|^2_{L^2(\rho^*)}$ that is commonly used in the score matching literature, highlighting the curse of dimensionality where sample complexity for accurate score estimation grows exponentially with the dimension $d$. Leveraging key insights in empirical Bayes theory as well as a new convergence rate of smoothed empirical distribution in Hellinger distance, we show that a regularized score estimator based on a Gaussian kernel attains this rate, shown optimal by a matching minimax lower bound. We also discuss extensions to estimating $\beta$-H\"older continuous scores with $\beta \leq 1$, as well as the implication of our theory on the sample complexity of score-based generative models.

📄 PDF Abstract BibTeX arXiv:2402.07747

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Blurs Behave Like Ensembles: Spatial Smoothings to Improve Accuracy, Uncertainty, and Robustness

2021-05-26 · Namuk Park, Songkuk Kim

Neural network ensembles, such as Bayesian neural networks (BNNs), have shown success in the areas of uncertainty estimation and robustness. However, a crucial challenge prohibits their use in practice. BNNs require a la…

Optimally adaptive Bayesian spectral density estimation for stationary and nonstationary processes

2020-03-04 · Nick James, Max Menzies

This article improves on existing methods to estimate the spectral density of stationary and nonstationary time series assuming a Gaussian process prior. By optimising an appropriate eigendecomposition using a smoothing …

Density EstimationTime SeriesTime Series Analysis

Logarithmic Smoothing for Adaptive PAC-Bayesian Off-Policy Learning

2025-06-12 · Maxime Haddouche, Otmane Sakhi

Off-policy learning serves as the primary framework for learning optimal policies from logged interactions collected under a static behavior policy. In this work, we investigate the more practical and flexible setting of…

BLENDS: Bayesian Learning-Enhanced Deep Smoothing for GNSS-Denied Environments

2026-06-21 · Nadav Cohen, Itzik Klein arxiv

Maintaining accurate navigation during GNSS outages remains a significant challenge for autonomous systems relying on low-cost inertial sensors. While classical smoothing methods, such as the two-filter smoother and Rauc…

Stein's unbiased risk estimate and Hyvärinen's score matching

2025-02-27 · Sulagna Ghosh, Nikolaos Ignatiadis, Frederic Koehler, Amber Lee

We study two G-modeling strategies for estimating the signal distribution (the empirical Bayesian's prior) from observations corrupted with normal noise. First, we choose the signal distribution by minimizing Stein's unb…