{"ID":2828142,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.19739","arxiv_id":"2512.19739","title":"OASI: Objective-Aware Surrogate Initialization for Multi-Objective Bayesian Optimization in TinyML Keyword Spotting","abstract":"Voice-triggered interfaces rely on keyword spotting (KWS) models that must operate continuously under strict memory, latency, and energy constraints on microcontroller-class hardware. Designing such models therefore requires not only high recognition accuracy but also predictable deployability within limited Flash and SRAM budgets. Bayesian optimization is known to handle accuracy-efficiency trade-offs effectively in multi-objective optimization; however, it is highly sensitive to initialization, particularly in the low-budget regimes of TinyML model optimization. We propose Objective-Aware Surrogate Initialization (OASI), which seeds surrogate optimization with Pareto-biased solutions generated via multi-objective simulated annealing. Unlike space-filling or heuristic warm-start methods, OASI initializes the surrogate conditioning process with a bias toward feasible accuracy-memory trade-offs, thus avoiding SRAM-violating configurations. OASI improves hypervolume and convergence robustness over Latin hypercube, Sobol, and random initializations under the same budget constraints on a TinyML KWS problem. Hardware-in-the-loop experiments on STM32 microcontrollers verify the existence of deployable and memory-feasible models without incurring extra optimization costs.","short_abstract":"Voice-triggered interfaces rely on keyword spotting (KWS) models that must operate continuously under strict memory, latency, and energy constraints on microcontroller-class hardware. Designing such models therefore requires not only high recognition accuracy but also predictable deployability within limited Flash and...","url_abs":"https://arxiv.org/abs/2512.19739","url_pdf":"https://arxiv.org/pdf/2512.19739v2","authors":"[\"Soumen Garai\",\"Danilo Pau\",\"Suman Samui\"]","published":"2025-12-17T17:32:33Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.SD\"]","methods":"[]","has_code":false}