Gradient-free training of neural ODEs for system identification and control using ensemble Kalman inversion
Ensemble Kalman inversion (EKI) is a sequential Monte Carlo method used to solve inverse problems within a Bayesian framework. Unlike backpropagation, EKI is a gradient-free optimization method that only necessitates the evaluation of artificial neural networks in forward passes. In this study, we examine the effectiveness of EKI in training neural ordinary differential equations (neural ODEs) for system identification and control tasks. To apply EKI to optimal control problems, we formulate inverse problems that incorporate a Tikhonov-type regularization term. Our numerical results demonstrate that EKI is an efficient method for training neural ODEs in system identification and optimal control problems, with runtime and quality of solutions that are competitive with commonly used gradient-based optimizers.
Code (1)
Similar Papers 제목 키워드 기반
StarNet: Gradient-free Training of Deep Generative Models using Determined System of Linear Equations
In this paper we present an approach for training deep generative models solely based on solving determined systems of linear equations. A network that uses this approach, called a StarNet, has the following desirable pr…
Online Policy Gradient for Model Free Learning of Linear Quadratic Regulators with $\sqrt{T}$ Regret
We consider the task of learning to control a linear dynamical system under fixed quadratic costs, known as the Linear Quadratic Regulator (LQR) problem. While model-free approaches are often favorable in practice, thus …
GBA: A Tuning-free Approach to Switch between Synchronous and Asynchronous Training for Recommendation Model
High-concurrency asynchronous training upon parameter server (PS) architecture and high-performance synchronous training upon all-reduce (AR) architecture are the most commonly deployed distributed training modes for rec…
Recommendation SystemsOutlier Gradient Analysis: Efficiently Identifying Detrimental Training Samples for Deep Learning Models
A core data-centric learning challenge is the identification of training samples that are detrimental to model performance. Influence functions serve as a prominent tool for this task and offer a robust framework for ass…
From Fourier to Neural ODEs: Flow Matching for Modeling Complex Systems
Modeling complex systems using standard neural ordinary differential equations (NODEs) often faces some essential challenges, including high computational costs and susceptibility to local optima. To address these challe…