arXiv:2607. 05461v1 Announce Type: cross Abstract: Existing methods for testing deep neural networks (DNNs) primarily prioritize test inputs likely to reveal model faults under a fixed labeling budget.
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.
arXiv:2607. 20046v1 Announce Type: cross Abstract: With the widespread deployment of deep neural networks (DNNs) in safety-critical domains, reducing the cost of model validation under limited testing budgets has become increasingly important.
arXiv:2606. 04310v1 Announce Type: new Abstract: Deep Neural Networks (DNNs) are increasingly being deployed in security-critical and safety-sensitive applications, which makes rigorous testing essential to identify and mitigate model weaknesses.
arXiv:2606. 26492v1 Announce Type: cross Abstract: Deep Learning (DL) programs can fail during training for many reasons, and diagnosing the cause is a costly and time-consuming maintenance task.
arXiv:2607. 12868v1 Announce Type: cross Abstract: Deep learning systems often fail due to subtle implementation faults that alter training behavior.
arXiv:2606. 04314v1 Announce Type: new Abstract: As neural networks are increasingly deployed in safety-critical domains, testing is essential to evaluate and improve their reliability.
TreeFI is a value‑aware statistical fault‑injection technique for FP32 single‑bit faults in deep neural network activations and weights. It partitions each layer’s value distribution into intervals with similar expected bit‑flip behavior using regression trees, then allocates injections across these intervals based on their relevance for failure‑rate estimation. This stratified approach preserves target confidence and error margins while dramatically reducing the required injection budget—up to 72.1× for activations and 11.2× for weights compared to existing baselines.
ExpTest is an autonomous learning‑rate controller that uses the training loss curve as an online signal to perform sequential statistical tests on theoretically motivated windows, detecting convergent behavior and triggering learning‑rate reductions. It combines a covariance‑based initial learning‑rate estimate, curvature‑motivated window sizing, and a two‑phase test‑driven decay, relying on the approximately exponential decay predicted under linearized network dynamics. Experiments on regression, classification, forecasting, and natural‑language tasks across various architectures show that ExpTest achieves competitive performance compared to hand‑tuned SGD baselines and recent learning‑rate‑free methods, without requiring manual initial learning‑rate selection or predefined scheduling.
The paper introduces Active Testing, a framework that selects the most informative test samples for annotation in NLP, aiming to reduce human effort while accurately estimating model performance. Experiments across 18 datasets and 4 embedding strategies show up to 95% annotation savings with less than 1% loss in performance estimation accuracy. The authors also propose an adaptive stopping criterion to determine the optimal number of samples without a predefined budget.
arXiv:2606. 15237v1 Announce Type: cross Abstract: Ensemble classifiers are predictive models that combine the results of simpler base models, often by majority vote.
arXiv:2608. 12144v1 Announce Type: cross Abstract: Over the past decade, many test adequacy metrics have been proposed for deep learning that characterize test dataset adequacy from different perspectives, e.
arXiv:2607. 08522v1 Announce Type: new Abstract: The inherent rigidity of fixed-size benchmarks makes them an inefficient tool for model evaluation.