Random Feature Approximation for Online Nonlinear Graph Topology Identification

10/19/2021
by   Rohan Money, et al.
0

Online topology estimation of graph-connected time series is challenging, especially since the causal dependencies in many real-world networks are nonlinear. In this paper, we propose a kernel-based algorithm for graph topology estimation. The algorithm uses a Fourier-based Random feature approximation to tackle the curse of dimensionality associated with the kernel representations. Exploiting the fact that the real-world networks often exhibit sparse topologies, we propose a group lasso based optimization framework, which is solve using an iterative composite objective mirror descent method, yielding an online algorithm with fixed computational complexity per iteration. The experiments conducted on real and synthetic data show that the proposed method outperforms its competitors.

READ FULL TEXT
research
06/01/2021

Leveraging Pre-Images to Discover Nonlinear Relationships in Multivariate Environments

Causal discovery, beyond the inference of a network as a collection of c...
research
03/08/2020

Nonlinear least-squares spline fitting with variable knots

In this paper, we present a nonlinear least-squares fitting algorithm us...
research
01/25/2021

Optimizing Convergence for Iterative Learning of ARIMA for Stationary Time Series

Forecasting of time series in continuous systems becomes an increasingly...
research
08/08/2022

Recovering the Graph Underlying Networked Dynamical Systems under Partial Observability: A Deep Learning Approach

We study the problem of graph structure identification, i.e., of recover...
research
05/10/2016

Kernel-Based Structural Equation Models for Topology Identification of Directed Networks

Structural equation models (SEMs) have been widely adopted for inference...
research
09/23/2022

GSP-Based MAP Estimation of Graph Signals

In this paper, we consider the problem of recovering random graph signal...
research
09/09/2020

1-Dimensional polynomial neural networks for audio signal related problems

In addition to being extremely non-linear, modern problems require milli...

Please sign up or login with your details

Forgot password? Click here to reset