arXiv Machine Learning
Online simultaneous inference for quantiles via smoothed stochastic gradient descent
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
2d ago
Online Inference for Quantile Distributional Reinforcement Learning
arXiv:2608. 12973v3 Announce Type: replace-cross Abstract: In this paper, we study online statistical inference for quantile-based distributional policy evaluation, which aims to characterize the distribution of discounted cumulative rewards under a given policy.
arXiv Machine Learning
Aug 3
Statistical Inference for Stochastic Gradient Descent: Beyond Finite Variance
arXiv:2605. 26000v2 Announce Type: replace-cross Abstract: Stochastic gradient descent (SGD) is foundational to large-scale statistical learning and stochastic optimization.
arXiv Machine Learning
Sep 14
Quantile-based Loss Filtering for Outlier-Robust Stochastic Gradient Descent
arXiv:2609. 13040v1 Announce Type: new Abstract: We study loss-based filtering for finite-sum optimization with a subset of corrupted component functions whose gradients may be highly unreliable.
arXiv Machine Learning
Aug 11
Conditional Diffusion for Nonparametric Instrumental Variable Quantile Regression
arXiv:2608. 08204v1 Announce Type: cross Abstract: This work proposes deep nonparametric Instrumental variable quantile regression (IVQR), a two-stage estimator that combines conditional diffusion modeling with a kernel-smoothed conditional moment formulation.
arXiv Machine Learning
Jun 30
Adaptive Iterative Hard Thresholding for Online High-dimensional Quantile Regression
arXiv:2606. 28652v1 Announce Type: cross Abstract: Online high-dimensional regression requires algorithms that can update sequentially while preserving structural sparsity.
arXiv Machine Learning
5d ago
Stochastic Gradient Descent: A Nonlinear Time Series Perspective
This paper studies the statistical properties of Stochastic Gradient Descent (SGD) with a constant step size using the framework of iterated random functions. It demonstrates convergence in Euclidean distance via Geometric Moment Contraction, establishes quenched central limit theorems, invariance principles, and α-stable convergence for averaged SGD regardless of initialization, and explores the effect of step sizes through derivative processes. The authors further develop a Richardson-Romberg extrapolation with multiple step sizes, propose a bias-reduced variant, and introduce an online inference method that yields empirical confidence intervals with coverage approaching nominal levels as sample size increases.