Online Ensemble Multi-kernel Learning Adaptive to Non-stationary and Adversarial Environments

12/28/2017
by   Yanning Shen, et al.
0

Kernel-based methods exhibit well-documented performance in various nonlinear learning tasks. Most of them rely on a preselected kernel, whose prudent choice presumes task-specific prior information. To cope with this limitation, multi-kernel learning has gained popularity thanks to its flexibility in choosing kernels from a prescribed kernel dictionary. Leveraging the random feature approximation and its recent orthogonality-promoting variant, the present contribution develops an online multi-kernel learning scheme to infer the intended nonlinear function `on the fly.' To further boost performance in non-stationary environments, an adaptive multi-kernel learning scheme (termed AdaRaker) is developed with affordable computation and memory complexity. Performance is analyzed in terms of both static and dynamic regret. To our best knowledge, AdaRaker is the first algorithm that can optimally track nonlinear functions in non-stationary settings with theoretical guarantees. Numerical tests on real datasets are carried out to showcase the effectiveness of the proposed algorithms.

READ FULL TEXT
research
12/28/2017

Random Feature-based Online Multi-kernel Learning in Environments with Unknown Dynamics

Kernel-based methods exhibit well-documented performance in various nonl...
research
05/07/2020

Active Learning with Multiple Kernels

Online multiple kernel learning (OMKL) has provided an attractive perfor...
research
02/09/2021

Graph-Aided Online Multi-Kernel Learning

Multi-kernel learning (MKL) has been widely used in function approximati...
research
09/16/2023

Efficient Methods for Non-stationary Online Learning

Non-stationary online learning has drawn much attention in recent years....
research
06/30/2020

Dynamic Regret of Policy Optimization in Non-stationary Environments

We consider reinforcement learning (RL) in episodic MDPs with adversaria...
research
09/12/2019

Nonstationary Nonparametric Online Learning: Balancing Dynamic Regret and Model Parsimony

An open challenge in supervised learning is conceptual drift: a data poi...
research
02/14/2018

Online Learning for Non-Stationary A/B Tests

The rollout of new versions of a feature in modern applications is a man...

Please sign up or login with your details

Forgot password? Click here to reset