OASI: Objective-Aware Surrogate Initialization for Multi-Objective Bayesian Optimization in TinyML Keyword Spotting

This article introduces OASI, a method for improving multi-objective Bayesian optimization in TinyML, specifically for keyword spotting. The focus is on initializing surrogate models in a way that is aware of the objectives. The source is ArXiv, indicating a research paper.

• •Focuses on multi-objective Bayesian optimization.
• •Applies to TinyML keyword spotting.
• •Introduces a novel initialization method (OASI).
• •Published on ArXiv, indicating a research paper.