Hyperparameter Optimization as a Service on INFN Cloud

TL;DR

This paper presents Hopaas, a cloud-based hyperparameter optimization service utilizing REST APIs, Bayesian algorithms, and multi-site resources to enhance machine learning model tuning, demonstrated through applications in high-energy physics simulations.

Contribution

Introduction of Hopaas, a novel cloud service for hyperparameter optimization using REST APIs, Bayesian methods, and multi-site resources to improve efficiency and scalability.

Findings

Enabled multi-node hyperparameter optimization campaigns.

Significantly improved parameterizations for LHCb experiment simulations.

Demonstrated effective use of INFN Cloud and CINECA resources.

Abstract

The simplest and often most effective way of parallelizing the training of complex machine learning models is to execute several training instances on multiple machines, scanning the hyperparameter space to optimize the underlying statistical model and the learning procedure. Often, such a meta-learning procedure is limited by the ability of accessing securely a common database organizing the knowledge of the previous and ongoing trials. Exploiting opportunistic GPUs provided in different environments represents a further challenge when designing such optimization campaigns. In this contribution, we discuss how a set of REST APIs can be used to access a dedicated service based on INFN Cloud to monitor and coordinate multiple training instances, with gradient-less optimization techniques, via simple HTTP requests. The service, called Hopaas (Hyperparameter OPtimization As A Service), is made of a web interface and sets of APIs implemented with a FastAPI backend running through Uvicorn and NGINX in a virtual instance of INFN Cloud. The optimization algorithms are currently based on Bayesian techniques as provided by Optuna. A Python frontend is also made available for quick prototyping. We present applications to hyperparameter optimization campaigns performed by combining private, INFN Cloud, and CINECA resources. Such multi-node multi-site optimization studies have given a significant boost to the development of a set of parameterizations for the ultra-fast simulation of the LHCb experiment.