Combining Multi-Objective Bayesian Optimization with Reinforcement Learning for TinyML
Deploying deep neural networks (DNNs) on microcontrollers (TinyML) is a common trend to process the increasing amount of sensor data generated at the edge, but in practice, resource and latency constraints make it difficult to find optimal DNN candidates. Neural architecture search (NAS) is an excellent approach to automate this search and can easily be combined with DNN compression techniques commonly used in TinyML. However, many NAS techniques are not only computationally expensive, especially hyperparameter optimization (HPO), but also often focus on optimizing only a single objective, e.g., maximizing accuracy, without considering additional objectives such as memory requirements or computational complexity of a DNN, which are key to making deployment at the edge feasible. In this paper, we propose a novel NAS strategy for TinyML based on multi-objective Bayesian optimization (MOBOpt) and an ensemble of competing parametric policies trained using Augmented Random Search (ARS) reinforcement learning (RL) agents. Our methodology aims at efficiently finding tradeoffs between a DNN's predictive accuracy, memory requirements on a given target system, and computational complexity. Our experiments show that we consistently outperform existing MOBOpt approaches on different datasets and architectures such as ResNet-18 and MobileNetV3.
Code (0)
등록된 구현이 없습니다.
Tasks
Bayesian OptimizationHyperparameter OptimizationNetwork PruningNeural Architecture SearchQuantizationreinforcement-learningReinforcement LearningReinforcement Learning (RL)Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning
We present a tutorial on Bayesian optimization, a method of finding the maximum of expensive cost functions. Bayesian optimization employs the Bayesian technique of setting a prior over the objective function and combini…
Bayesian OptimizationHierarchical Reinforcement LearningHyperparameter Optimizationreinforcement-learning+2Computer-Aided Multi-Objective Optimization in Small Molecule Discovery
Molecular discovery is a multi-objective optimization problem that requires identifying a molecule or set of molecules that balance multiple, often competing, properties. Multi-objective molecular design is commonly addr…
Bayesian OptimizationApproximating Pareto Frontier through Bayesian-optimization-directed Robust Multi-objective Reinforcement Learning
Many real-word decision or control problems involve multiple conflicting objectives and uncertainties, which requires learned policies are not only Pareto optimal but also robust. In this paper, we proposed a novel algor…
Bayesian OptimizationDiversityMulti-Objective Reinforcement Learningreinforcement-learning+2Robust Model-free Reinforcement Learning with Multi-objective Bayesian Optimization
In reinforcement learning (RL), an autonomous agent learns to perform complex tasks by maximizing an exogenous reward signal while interacting with its environment. In real-world applications, test conditions may differ …
Bayesian Optimizationreinforcement-learningReinforcement LearningReinforcement Learning (RL)Concave Utility Reinforcement Learning with Zero-Constraint Violations
We consider the problem of tabular infinite horizon concave utility reinforcement learning (CURL) with convex constraints. For this, we propose a model-based learning algorithm that also achieves zero constraint violatio…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)