mlsanityData to 14 Oct 2026

EARL: Energy-Aware Optimization of Liquid State Machines for Pervasive AI

arXiv 2601.05205 ↗First posted 8 Jan 2026cs.LG cs.PFcited by 0

On the map: Deep reinforcement learning methods → RL for energy, networks and operations

Abstract (arXiv)

Pervasive AI increasingly depends on on-device learning systems that deliver low-latency and energy-efficient computation under strict resource constraints. Liquid State Machines (LSMs) offer a promising approach for low-power temporal processing in pervasive and neuromorphic systems, but their deployment remains challenging due to high hyperparameter sensitivity and the computational cost of traditional optimization methods that ignore energy constraints. This work presents EARL, an energy-aware reinforcement learning framework that integrates Bayesian optimization with an adaptive reinforcement learning based selection policy to jointly optimize accuracy and energy consumption. EARL employs surrogate modeling for global exploration, reinforcement learning for dynamic candidate prioritization, and an early termination mechanism to eliminate redundant evaluations, substantially reducing computational overhead. Experiments on three benchmark datasets demonstrate that EARL achieves 6 to 15 percent higher accuracy, 60 to 80 percent lower energy consumption, and up to an order of magnitude reduction in optimization time compared to leading hyperparameter tuning frameworks. These results highlight the effectiveness of energy-aware adaptive search in improving the efficiency and scalability of LSMs for resource-constrained on-device AI applications.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods. Builds on 6 of its 18 references that are in the map. First posted on arXiv 8 Jan 2026.

Builds on

6 of 18 references.

References · 6

  1. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  2. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,501
  3. 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,254
  4. 2016Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimizationcited by 699
  5. 2017Ray: A Distributed Framework for Emerging AI Applicationscited by 527
  6. 2018Reservoir computing approaches for representation and classification of multivariate time seriescited by 38

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Hybrid Energy-Aware Reward Shaping: A Unified Lightweight Physics-Guided Methodology for Policy Optimization
  2. 2026All On-Board: Fully On-Chip Neuromorphic Q-Learning with Embedded CartPole Simulation
  3. 2026Energy Efficient Software Hardware CoDesign for Machine Learning: From TinyML to Large Language Models
  4. 2025Multi-Objective Reinforcement Learning for Energy-Efficient Industrial Control
  5. 2026Sample-Efficient Pareto Front Modeling for Energy-Aware Reinforcement Learning Using Bayesian Optimization
  6. 2025LC-Opt: Benchmarking Reinforcement Learning and Agentic AI for End-to-End Liquid Cooling Optimization in Data Centers
  7. 2025Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks
  8. 2025Hardware-Aware Fine-Tuning of Spiking Q-Networks on the SpiNNaker2 Neuromorphic Platform