mlsanityData to 14 Oct 2026

TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML

arXiv 2508.12905 ↗First posted 18 Aug 2025cs.LG cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

We introduce TCUQ, a single pass, label free uncertainty monitor for streaming TinyML that converts short horizon temporal consistency captured via lightweight signals on posteriors and features into a calibrated risk score with an O(W ) ring buffer and O(1) per step updates. A streaming conformal layer turns this score into a budgeted accept/abstain rule, yielding calibrated behavior without online labels or extra forward passes. On microcontrollers, TCUQ fits comfortably on kilobyte scale devices and reduces footprint and latency versus early exit and deep ensembles (typically about 50 to 60% smaller and about 30 to 45% faster), while methods of similar accuracy often run out of memory. Under corrupted in distribution streams, TCUQ improves accuracy drop detection by 3 to 7 AUPRC points and reaches up to 0.86 AUPRC at high severities; for failure detection it attains up to 0.92 AUROC. These results show that temporal consistency, coupled with streaming conformal calibration, provides a practical and resource efficient foundation for on device monitoring in TinyML.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 36 of its 49 references that are in the map. First posted on arXiv 18 Aug 2025.

Builds on

36 of 49 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2017On Calibration of Modern Neural Networkscited by 4,960
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  4. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  5. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  6. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  7. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  8. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  9. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  10. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,287
  11. 2017Selective Classification for Deep Neural Networkscited by 852
  12. 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 792
24 more
  1. 2018Speech Commands: A Dataset for Limited-Vocabulary Speech Recognitioncited by 752
  2. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 732
  3. 2017BranchyNet: Fast Inference via Early Exiting from Deep Neural Networkscited by 596
  4. 2018Predictive Uncertainty Estimation via Prior Networkscited by 557
  5. 2019Measuring Calibration in Deep Learningcited by 446
  6. 2021Adaptive Conformal Inference Under Distribution Shiftcited by 375
  7. 2019SelectiveNet: A Deep Neural Network with an Integrated Reject Optioncited by 350
  8. 2024MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Casescited by 223
  9. 2021Deep Deterministic Uncertainty: A Simple Baselinecited by 200
  10. 2020Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Countscited by 164
  11. 2020Uncertainty Quantification and Deep Ensemblescited by 139
  12. 2019MNIST-C: A Robustness Benchmark for Computer Visioncited by 138
  13. 2021MLPerf Tiny Benchmarkcited by 124
  14. 2017Hello Edge: Keyword Spotting on Microcontrollerscited by 110
  15. 2024A Review on Edge Large Language Models: Design, Execution, and Applicationscited by 100
  16. 2020Getting a CLUE: A Method for Explaining Uncertainty Estimatescited by 92
  17. 2023Uncertainty Estimation by Fisher Information-based Evidential Deep Learningcited by 58
  18. 2020Hydra: Preserving Ensemble Diversity for Model Distillationcited by 31
  19. 2021Transformer Uncertainty Estimation with Hierarchical Stochastic Attentioncited by 21
  20. 2023Fixing Overconfidence in Dynamic Neural Networkscited by 19
  21. 2023Window-Based Early-Exit Cascades for Uncertainty Estimation: When Deep Ensembles are More Efficient than Single Modelscited by 16
  22. 2023Towards Anytime Classification in Early-Exit Architectures by Enforcing Conditional Monotonicitycited by 16
  23. 2022T-RECX: Tiny-Resource Efficient Convolutional neural networks with early-eXitcited by 5
  24. 2024QUTE: Quantifying Uncertainty in TinyML with Early-exit-assisted ensembles for model-monitoringcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025SNAP-UQ: Self-supervised Next-Activation Prediction for Single-Pass Uncertainty in TinyML
  2. 2022An Empirical Study of Low Precision Quantization for TinyML
  3. 2024UR2M: Uncertainty and Resource-Aware Event Detection on Microcontrollers
  4. 2026MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference
  5. 2026Displacement Is Not Direction: Evaluating Fidelity Metrics for Quantized LLM Deployment
  6. 2025CalexNet: Soft Cascade-Aligned Training and Calibration for Lightweight Early-Exit Branches
  7. 2025Safety-Preserving PTQ via Contrastive Alignment Loss
  8. 2026Beyond Outliers: A Data-Free Layer-wise Mixed-Precision Quantization Approach Driven by Numerical and Structural Dual-Sensitivity