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

by   Audrey Durand, et al.

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 for finite-dimensional linear regression with fixed regularization and known variance to the kernel setup with a regularization parameter allowed to be a measurable function of past observations. Then, using appropriate self-normalized inequalities we build upper and lower bound estimates for the variance, leading to Bersntein-like concentration bounds. The later is used in order to define the adaptive regularization. The bounds resulting from our technique are valid uniformly over all observation points and all time steps, and are compared against the literature with numerical experiments. Finally, the potential of these tools is illustrated by an application to kernelized bandits, where we revisit the Kernel UCB and Kernel Thompson Sampling procedures, and show the benefits of the novel adaptive kernel tuning strategy.


Information Directed Sampling and Bandits with Heteroscedastic Noise

In the stochastic bandit problem, the goal is to maximize an unknown fun...

Adaptive Importance Sampling meets Mirror Descent: a Bias-variance tradeoff

Adaptive importance sampling is a widely spread Monte Carlo technique th...

Data-driven calibration of linear estimators with minimal penalties

This paper tackles the problem of selecting among several linear estimat...

Error analysis of regularized trigonometric linear regression with unbounded sampling: a statistical learning viewpoint

The effectiveness of non-parametric, kernel-based methods for function e...

Adaptive regularization for Lasso models in the context of non-stationary data streams

Large scale, streaming datasets are ubiquitous in modern machine learnin...

Order-Optimal Error Bounds for Noisy Kernel-Based Bayesian Quadrature

In this paper, we study the sample complexity of noisy Bayesian quadratu...

Please sign up or login with your details

Forgot password? Click here to reset