EARL让液态机在低功耗设备上更快更省地训练。
EARL: Energy-Aware Optimization of Liquid State Machines for Pervasive AI
- 用强化学习+贝叶斯优化联合调参，兼顾准确率与能耗。
- 相比主流方法，能耗降60%~80%，速度提升十倍。
- 适合做嵌入式、神经形态计算的实时低功耗系统。
普适人工智能越来越依赖于能在严格资源约束下实现低延迟、低功耗计算的本地学习系统。液态状态机（LSMs）为普适与类脑系统中的低功耗时序处理提供了有前景的解决方案，但其部署仍面临超参数敏感性强以及传统优化方法计算成本高且忽略能耗的问题。本文提出EARL，一种融合贝叶斯优化与自适应强化学习选择策略的能量感知强化学习框架，可联合优化准确率与能耗。EARL采用代理建模进行全局探索，利用强化学习动态优先候选解，并引入早期终止机制消除冗余评估，显著降低计算开销。在三个基准数据集上的实验表明，相较于领先的超参数调优框架，EARL实现了6%~15%更高的准确率、60%~80%更低的能耗，优化时间最多减少一个数量级。结果表明，能量感知的自适应搜索能有效提升LSM在资源受限的本地AI应用中的效率与可扩展性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。