Adaptive Kernel Learning in Heterogeneous Networks

08/01/2019
by   Hrusikesha Pradhan, et al.
3

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.

READ FULL TEXT

page 1

page 10

10/11/2017

Decentralized Online Learning with Kernels

We consider multi-agent stochastic optimization problems over reproducin...
05/23/2022

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

In recent years, decentralized learning has emerged as a powerful tool n...
12/08/2020

A Primal-Dual Framework for Decentralized Stochastic Optimization

We consider the decentralized convex optimization problem, where multipl...
04/13/2016

Algorithms for stochastic optimization with expectation constraints

This paper considers the problem of minimizing an expectation function o...
01/28/2020

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

This paper studies the decentralized optimization and learning problem w...
04/19/2018

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

We consider Markov Decision Problems defined over continuous state and a...
08/04/2022

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

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