Adaptive Kernel Learning in Heterogeneous Networks

by   Hrusikesha Pradhan, et al.

We consider the framework of learning over decentralized networks, where nodes observe unique, possibly correlated, observation streams. We focus on the case where agents learn a regression function that belongs to a reproducing kernel Hilbert space (RKHS). In this setting, a decentralized network aims to learn nonlinear statistical models that are optimal in terms of a global stochastic convex functional that aggregates data across the network, with only access to a local data stream. We incentivize coordination while respecting network heterogeneity through the introduction of nonlinear proximity constraints. To solve it, we propose applying a functional variant of stochastic primal-dual (Arrow-Hurwicz) method which yields a decentralized algorithm. To handle the fact that the RKHS parameterization has complexity proportionate with the iteration index, we project the primal iterates onto Hilbert subspaces that are greedily constructed from the observation sequence of each node. The resulting proximal stochastic variant of Arrow-Hurwicz, dubbed Heterogeneous Adaptive Learning with Kernels (HALK), is shown to converge in expectation, both in terms of primal sub-optimality and constraint violation to a neighborhood that depends on a given constant step-size selection. Simulations on a correlated spatio-temporal random field estimation problem validate our theoretical results, which are born out in practice for networked oceanic sensing buoys estimating temperature and salinity from depth measurements.


page 1

page 10


Decentralized Online Learning with Kernels

We consider multi-agent stochastic optimization problems over reproducin...

Theoretical Analysis of Primal-Dual Algorithm for Non-Convex Stochastic Decentralized Optimization

In recent years, decentralized learning has emerged as a powerful tool n...

A Primal-Dual Framework for Decentralized Stochastic Optimization

We consider the decentralized convex optimization problem, where multipl...

Algorithms for stochastic optimization with expectation constraints

This paper considers the problem of minimizing an expectation function o...

COKE: Communication-Censored Kernel Learning for Decentralized Non-parametric Learning

This paper studies the decentralized optimization and learning problem w...

Nonparametric Stochastic Compositional Gradient Descent for Q-Learning in Continuous Markov Decision Problems

We consider Markov Decision Problems defined over continuous state and a...

QC-ODKLA: Quantized and Communication-Censored Online Decentralized Kernel Learning via Linearized ADMM

This paper focuses on online kernel learning over a decentralized networ...