{"ID":3084645,"CreatedAt":"2026-06-05T06:46:15.197025399Z","UpdatedAt":"2026-06-06T19:15:30.205453645Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.05373","arxiv_id":"2606.05373","title":"Evidence-Guided Neural Architecture Selection under Uncertainty for Subject-Specific Blood Glucose Forecasting","abstract":"Reliable neural architecture selection is an open challenge in time-series forecasting under limited, noisy, and heterogeneous data, where standard heuristic architecture design and validation approaches fail to ensure accurate and reliable prediction and generalization. We propose EVIDENT (EVidence-based IDEntification of Neural archiTectures), a framework for architecture selection that integrates Bayesian training, evidence-based ranking, and task-specific validation under uncertainty. The framework explores the candidate architecture pool and identifies the lowest-capacity model that satisfies a prescribed validation criterion. We demonstrate this method using temporal convolutional networks (TCNs) for individualized blood glucose forecasting in type 1 diabetes patients. The results show that EVIDENT systematically rejects both under- and over-parameterized TCN architectures on population-level diabetes data, while identifying models that generalize reliably to unseen patients. When multiple architectures are competitive, the framework further supports plausibility-weighted ensemble predictions that enhance predictive performance. Compared with a random-search baseline, EVIDENT identified smaller architectures with more consistent forecasting performance on unseen patients. These findings establish EVIDENT as a strategy to neural architecture discovery, enabling reliable model selection for high-consequence forecasting in data-limited and heterogeneous settings.","short_abstract":"Reliable neural architecture selection is an open challenge in time-series forecasting under limited, noisy, and heterogeneous data, where standard heuristic architecture design and validation approaches fail to ensure accurate and reliable prediction and generalization. We propose EVIDENT (EVidence-based IDEntificatio...","url_abs":"https://arxiv.org/abs/2606.05373","url_pdf":"https://arxiv.org/pdf/2606.05373v1","authors":"[\"Md Azharul Islam\",\"Dwyer Deighan\",\"Tarunraj Singha\",\"Danial Faghihi\"]","published":"2026-06-03T19:20:11Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"physics.bio-ph\"]","methods":"[]","has_code":false}