analiza aiqbench
This research explores optimizing TinyML inference by adjusting decision thresholds via instance hardness pruning, offering a method to balance energy consumption against classification accuracy on resource-constrained devices. As AI systems scale, such techniques are critical for achieving the environmental sustainability required in edge computing and IoT applications where power budgets are tight. The study presents preliminary proof-of-concept results demonstrating that computational complexity can be managed without significantly degrading model performance.
On the Instance Hardness as a Decision Criterion in TinyML Systems
arXiv:2608.29913v1 Announce Type: new Abstract: TinyML includes the implementation of machine learning on devices with limited memory and computing resources. With the development of technology, AI systems continue to scale in terms of size and computational requirements. This forces researchers to adapt methods to be environmentally sustainable by designing techniques for reducing computational costs and energy consumption in inferring AI models, even in small devices. In this work, we present preliminary findings on a novel application of the tree depth prune instance hardness method to the TinyML system. The results indicate that threshold control can change energy consumption with limited classification quality changes. This method allows us to adjust classification accuracy, thereby influencing computational complexity and energy consumption for inference. We present a work in progress with initial results as a proof of concept.
Abstract:TinyML includes the implementation of machine learning on devices with limited memory and computing resources. With the development of technology, AI systems continue to scale in terms of size and computational requirements. This forces researchers to adapt methods to be environmentally sustainable by designing techniques for reducing computational costs and energy consumption in inferring AI models, even in small devices. In this work, we present preliminary findings on a novel application of the tree depth prune instance hardness method to the TinyML system. The results indicate that threshold control can change energy consumption with limited classification quality changes. This method allows us to adjust classification accuracy, thereby influencing computational complexity and energy consumption for inference. We present a work in progress with initial results as a proof of concept.
Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
arXiv:2608.29913 [cs.AI]
(or arXiv:2608.29913v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2608.29913 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 226 cuvinte
Subiecte conexe
Lattice-Based Cryptography Explained
Quantum Zeitgeist · 15 aug. 2026
Review of Fundamental Uncertainty.
LessWrong · 1 aug. 2026
Hint-based CoT faithfulness evals still mostly work on Claude
LessWrong · 30 iul. 2026
Expenditure Horizon: Measuring Optimization Ability, with an Application to NanoGPT
METR · 21 iul. 2026