6 papers
Profiling Lightweight Large Language Models
Tomohiro Harada, Enrique Alba, Gabriel Luque
Lightweight large language models (LLMs) are increasingly being deployed locally on personal computers and are expected to play a growing role in resource-constrained edge and mobi…
From Latent Space to Training Data: Explainable Specialization in Minimal MLPs
Enrique Alba, Ezequiel Lopez-Rubio
We here study whether training biases can make hidden neurons specialize in minimal one-hidden-layer MLPs, and whether such specialization improves prototype-based reconstruction o…
Energy-Aware Metaheuristics
Enrique Alba, Tomohiro Harada, Gabriel Luque
This paper presents a principled framework for designing energy-aware metaheuristics that operate under fixed energy budgets. We introduce a unified operator-level model that quant…
A Methodology for Effective Surrogate Learning in Complex Optimization
Tomohiro Harada, Enrique Alba, Gabriel Luque
Solving complex problems requires continuous effort in developing theory and practice to cope with larger, more difficult scenarios. Working with surrogates is normal for creating…
Green Optimization: Energy-aware Design of Metaheuristics by Using Machine Learning Surrogates to Cope with Real Problems
Tomohiro Harada, Enrique Alba, Gabriel Luque
Addressing real-world optimization challenges requires not only advanced metaheuristics but also continuous refinement of their internal mechanisms. This paper explores the integra…
Energy and Quality of Surrogate-Assisted Search Algorithms: a First Analysis
Tomohiro Harada, Enrique Alba, Gabriel Luque
Solving complex real problems often demands advanced algorithms, and then continuous improvements in the internal operations of a search technique are needed. Hybrid algorithms, pa…