Streaming kernel regression with provably adaptive mean, variance, and regularization

MaRDI QIDQ4558158zbMATH OpenFDO

Authors Audrey Durand, Odalric-Ambrym Maillard, Joelle Pineau

Publication date 21 November 2018

Full work available at URL https://arxiv.org/abs/1708.00768, http://jmlr.csail.mit.edu/papers/v19/17-404.html

zbMATH Keywords

regressionkernelonline learningadaptive tuningbandits

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Learning and adaptive systems in artificial intelligence (68T05) Online algorithms; streaming algorithms (68W27) Sequential estimation (62L12)

Recommendations

• Online regression with unbounded sampling
• \textsf{StreaMRAK} a streaming multi-resolution adaptive kernel algorithm
• Re-adapting the regularization of weights for non-stationary regression
• Online regression with varying Gaussians and non-identical distributions
• Nonparametric stochastic approximation with large step-sizes

Cites work

• scientific article; zbMATH DE number 107482 (Why is no real title available?)
• scientific article; zbMATH DE number 3273551 (Why is no real title available?)
• Finite-time analysis of the multiarmed bandit problem
• Gaussian processes for machine learning.
• Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting
• Linear Thompson sampling revisited
• Non‐parametric regression with wavelet kernels
• Penalized empirical risk minimization over Besov spaces
• Using trajectory data to improve Bayesian optimization for reinforcement learning

Cited in

(2)

• \textsf{StreaMRAK} a streaming multi-resolution adaptive kernel algorithm
• No-regret Bayesian optimization with unknown hyperparameters

Describes a project that uses

Uses Software

• Spearmint

This page was built for publication: Streaming kernel regression with provably adaptive mean, variance, and regularization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4558158)