Corpus ID: 10469182

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

@article{Durand2018StreamingKR,
  title={Streaming kernel regression with provably adaptive mean, variance, and regularization},
  author={A. Durand and O. Maillard and Joelle Pineau},
  journal={ArXiv},
  year={2018},
  volume={abs/1708.00768}
}
  • A. Durand, O. Maillard, Joelle Pineau
  • Published 2018
  • Mathematics, Computer Science
  • ArXiv
  • We consider the problem of streaming kernel regression, when the observations arrive sequentially and the goal is to recover the underlying mean function, assumed to belong to an RKHS. The variance of the noise is not assumed to be known. In this context, we tackle the problem of tuning the regularization parameter adaptively at each time step, while maintaining tight confidence bounds estimates on the value of the mean function at each point. To this end, we first generalize existing results… CONTINUE READING
    17 Citations
    Bayesian Optimization under Heavy-tailed Payoffs
    • 7
    • PDF
    No-regret Bayesian Optimization with Unknown Hyperparameters
    • 16
    • PDF
    Local Differential Privacy for Bayesian Optimization
    • 1
    • PDF
    Online Learning in Kernelized Markov Decision Processes
    • 10
    • PDF
    Stochastic Bandits with Context Distributions
    • 2
    • PDF
    L G ] 2 1 M ay 2 01 8 Online Learning in Kernelized Markov Decision Processes
    • Highly Influenced
    No-regret Algorithms for Multi-task Bayesian Optimization
    • 1
    • Highly Influenced
    • PDF
    Mathematics of Statistical Sequential Decision Making
    • 3

    References

    SHOWING 1-10 OF 26 REFERENCES
    Self-normalization techniques for streaming confident regression
    • 5
    • PDF
    Empirical Bernstein Bounds and Sample-Variance Penalization
    • 265
    • Highly Influential
    • PDF
    Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design
    • 1,194
    • Highly Influential
    • PDF
    Finite-Time Analysis of Kernelised Contextual Bandits
    • 90
    • Highly Influential
    • PDF
    Linear Thompson Sampling Revisited
    • 89
    • PDF
    Thompson Sampling for Contextual Bandits with Linear Payoffs
    • 486
    • PDF
    Contextual Gaussian Process Bandit Optimization
    • 218
    • PDF
    Gaussian Processes for Machine Learning
    • 13,775
    • PDF
    Practical Bayesian Optimization of Machine Learning Algorithms
    • 3,642
    • PDF