{"ID":6023657,"CreatedAt":"2026-07-08T01:00:23.257252134Z","UpdatedAt":"2026-07-09T01:07:32.349475501Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.05461","arxiv_id":"2607.05461","title":"AdaStop: Cost-Aware Early Stopping for DNN Test Selection","abstract":"Existing methods for testing deep neural networks (DNNs) primarily prioritize test inputs likely to reveal model faults under a fixed labeling budget. In practice, choosing that budget is difficult: too little testing misses failures, while too much incurs unnecessary labeling costs. This work studies the stopping problem in DNN testing. We formulate testing as a cost--benefit decision process in which labeling an input incurs cost $c$ and discovering a fault yields value $v$. Based on this formulation, we introduce \\textit{AdaStop}, a framework that estimates the marginal fault discovery rate during testing and stops labeling when the estimated rate falls below the threshold $τ= c/v$. Experiments across multiple datasets, architectures, and selection strategies show that $65$--$84\\%$ of faults can be discovered using only $9$--$31\\%$ of the labeling budget.","short_abstract":"Existing methods for testing deep neural networks (DNNs) primarily prioritize test inputs likely to reveal model faults under a fixed labeling budget. In practice, choosing that budget is difficult: too little testing misses failures, while too much incurs unnecessary labeling costs. This work studies the stopping prob...","url_abs":"https://arxiv.org/abs/2607.05461","url_pdf":"https://arxiv.org/pdf/2607.05461v1","authors":"[\"Bonan Shen\",\"Wei-Jung Huang\",\"Xin Liu\",\"Jiazhou Gao\",\"Tao Ning\"]","published":"2026-07-06T01:17:18Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[]","has_code":false}