mlsanityData to 7 Oct 2026

AdaStop: Cost-Aware Early Stopping for DNN Test Selection

arXiv 2607.05461 ↗First posted 6 Jul 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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 textitAdaStop, 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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 90 of its 103 references that are in the map. First posted on arXiv 6 Jul 2026.

Builds on

90 of 103 references.

References · 90

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  4. 2025Qwen3 Technical Reportcited by 8,195
  5. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  6. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  7. 2023Let's Verify Step by Stepcited by 3,598
  8. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  9. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,678
  10. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,414
  11. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  12. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
38 more
  1. 2022Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timecited by 1,366
  2. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,193
  3. 2019TinyBERT: Distilling BERT for Natural Language Understandingcited by 1,153
  4. 2022Editing Models with Task Arithmeticcited by 1,076
  5. 2022Scaling Laws for Reward Model Overoptimizationcited by 1,056
  6. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
  7. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
  8. 2024SimPO: Simple Preference Optimization with a Reference-Free Rewardcited by 951
  9. 2023A General Theoretical Paradigm to Understand Learning from Human Preferencescited by 906
  10. 2023On-Policy Distillation of Language Models: Learning from Self-Generated Mistakescited by 840
  11. 2016Sequence-Level Knowledge Distillationcited by 761
  12. 2022Discovering Latent Knowledge in Language Models Without Supervisioncited by 733
  13. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 691
  14. 2024Self-Rewarding Language Modelscited by 654
  15. 2019Improved Knowledge Distillation via Teacher Assistantcited by 567
  16. 2025Process Reinforcement through Implicit Rewardscited by 478
  17. 2025Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Modelcited by 450
  18. 2023Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervisioncited by 445
  19. 2018Scalable agent alignment via reward modeling: a research directioncited by 438
  20. 2026Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Modelscited by 386
  21. 2018AI safety via debatecited by 384
  22. 2019On the Efficacy of Knowledge Distillationcited by 377
  23. 2025OpenThoughts: Data Recipes for Reasoning Modelscited by 287
  24. 2026Reinforcement Learning via Self-Distillationcited by 285
  25. 2026Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipecited by 262
  26. 2025DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoningcited by 261
  27. 2024KTO: Model Alignment as Prospect Theoretic Optimizationcited by 256
  28. 2022Measuring Progress on Scalable Oversight for Large Language Modelscited by 212
  29. 2026Self-Distillation Enables Continual Learningcited by 212
  30. 2015Semi-supervised Sequence Learningcited by 198
  31. 2025AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning datasetcited by 165
  32. 2026MiMo-V2-Flash Technical Reportcited by 163
  33. 2025Skywork Open Reasoner 1 Technical Reportcited by 161
  34. 2026On-Policy Context Distillation for Language Modelscited by 161
  35. 2023DistillSpec: Improving Speculative Decoding via Knowledge Distillationcited by 160
  36. 2026Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolationcited by 157
  37. 2026Entropy-Aware On-Policy Distillation of Language Modelscited by 151
  38. 2026A Survey of On-Policy Distillation for Large Language Modelscited by 148

50 most cited of 90 All 90 (JSON)

Built on by

Not cited yet.