Cover Image

A Separation in Heavy-Tailed Sampling: Gaussian vs. Stable Oracles for Proximal Samplers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	He, Ye, Mousavi-Hosseini, Alireza, Balasubramanian, Krishnakumar, Erdogdu, Murat A.
Format:	Preprint
Published:	2024
Subjects:	Statistics Theory Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Riemannian Proximal Sampler for High-accuracy Sampling on Manifolds
by: Guan, Yunrui, et al.
Published: (2025)

Finite-Dimensional Gaussian Approximation for Deep Neural Networks: Universality in Random Weights
by: Balasubramanian, Krishnakumar, et al.
Published: (2025)

Dense associative memory for Gaussian distributions
by: Tankala, Chandan, et al.
Published: (2025)

Optimal Excess Risk Bounds for Empirical Risk Minimization on $p$-Norm Linear Regression
by: Hanchi, Ayoub El, et al.
Published: (2023)

Finite-Particle Convergence Rates for Conservative and Non-Conservative Drifting Models
by: Balasubramanian, Krishnakumar
Published: (2026)

Finite-Particle Rates for Regularized Stein Variational Gradient Descent
by: He, Ye, et al.
Published: (2026)

High-dimensional scaling limits and fluctuations of online least-squares SGD with smooth covariance
by: Balasubramanian, Krishnakumar, et al.
Published: (2023)

A Geometric Analysis of PCA
by: Hanchi, Ayoub El, et al.
Published: (2025)

Sampling from the Mean-Field Stationary Distribution
by: Kook, Yunbum, et al.
Published: (2024)

Post-Training with Policy Gradients: Optimality and the Base Model Barrier
by: Mousavi-Hosseini, Alireza, et al.
Published: (2026)

Multivariate Gaussian Approximation for Random Forest via Region-based Stabilization
by: Shi, Zhaoyang, et al.
Published: (2024)

Gaussian random field approximation via Stein's method with applications to wide random neural networks
by: Balasubramanian, Krishnakumar, et al.
Published: (2023)

Minimax Linear Regression under the Quantile Risk
by: Hanchi, Ayoub El, et al.
Published: (2024)

On the Efficiency of ERM in Feature Learning
by: Hanchi, Ayoub El, et al.
Published: (2024)

Meta-Learning with Generalized Ridge Regression: High-dimensional Asymptotics, Optimality and Hyper-covariance Estimation
by: Jin, Yanhao, et al.
Published: (2024)

Statistical Inference for Linear Functionals of Online Least-squares SGD when $t \gtrsim d^{1+δ}$
by: Agrawalla, Bhavya, et al.
Published: (2025)

Nonsmooth Nonparametric Regression via Fractional Laplacian Eigenmaps
by: Shi, Zhaoyang, et al.
Published: (2024)

Sparsified-Learning for High-Dimensional Heavy-Tailed Locally Stationary Time Series, Concentration and Oracle Inequalities
by: Wang, Yingjie, et al.
Published: (2025)

Gaussian and Bootstrap Approximation for Matching-based Average Treatment Effect Estimators
by: Shi, Zhaoyang, et al.
Published: (2024)

A Quantitative Characterization of Forgetting in Post-Training
by: Balasubramanian, Krishnakumar, et al.
Published: (2026)

Improved Finite-Particle Convergence Rates for Stein Variational Gradient Descent
by: Banerjee, Sayan, et al.
Published: (2024)

Learning Multi-Index Models with Neural Networks via Mean-Field Langevin Dynamics
by: Mousavi-Hosseini, Alireza, et al.
Published: (2024)

Robust Feature Learning for Multi-Index Models in High Dimensions
by: Mousavi-Hosseini, Alireza, et al.
Published: (2024)

Analysis of Langevin Monte Carlo from Poincaré to Log-Sobolev
by: Chewi, Sinho, et al.
Published: (2021)

Total Variation Rates for Riemannian Flow Matching
by: Guan, Yunrui, et al.
Published: (2026)

Diffusion Models with Heavy-Tailed Targets: Score Estimation and Sampling Guarantees
by: Yu, Yifeng, et al.
Published: (2026)

Fast Convergence of $Φ$-Divergence Along the Unadjusted Langevin Algorithm and Proximal Sampler
by: Mitra, Siddharth, et al.
Published: (2024)

Regularized Stein Variational Gradient Flow
by: He, Ye, et al.
Published: (2022)

Transformers Handle Endogeneity in In-Context Linear Regression
by: Liang, Haodong, et al.
Published: (2024)

Statistical Inference for Linear Functionals of Online SGD in High-dimensional Linear Regression
by: Agrawalla, Bhavya, et al.
Published: (2023)

From Information to Generative Exponent: Learning Rate Induces Phase Transitions in SGD
by: Tsiolis, Konstantinos Christopher, et al.
Published: (2025)

Asymptotic Classification Error for Heavy-Tailed Renewal Processes
by: Rong, Xinhui, et al.
Published: (2024)

When Do Transformers Outperform Feedforward and Recurrent Networks? A Statistical Perspective
by: Mousavi-Hosseini, Alireza, et al.
Published: (2025)

Privacy of SGD under Gaussian or Heavy-Tailed Noise: Guarantees without Gradient Clipping
by: Şimşekli, Umut, et al.
Published: (2024)

Differentially Private Two-Stage Gradient Descent for Instrumental Variable Regression
by: Liang, Haodong, et al.
Published: (2025)

Large-Sample Properties of Non-Stationary Source Separation for Gaussian Signals
by: Bachoc, François, et al.
Published: (2022)

A Simple and Optimal Policy Design with Safety against Heavy-Tailed Risk for Stochastic Bandits
by: Simchi-Levi, David, et al.
Published: (2022)

Mixing Time of the Proximal Sampler in Relative Fisher Information via Strong Data Processing Inequality
by: Wibisono, Andre
Published: (2025)

Variance Reduction for the Independent Metropolis Sampler
by: Liu, Siran, et al.
Published: (2024)

From Spikes to Heavy Tails: Unveiling the Spectral Evolution of Neural Networks
by: Kothapalli, Vignesh, et al.
Published: (2024)