mlsanityData to 14 Oct 2026

Quantizing Time-Series Models As Dynamical Systems: Trajectory-Based Quantization Sensitivity Score

arXiv 2606.13300 ↗First posted 11 Jun 2026cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

We introduce the Trajectory-based Quantization Sensitivity Score (TQS), a metric that reframes post-training quantization (PTQ) through the lens of dynamical-systems stability. By modeling the network's rollout as a discrete-time dynamical system, TQS characterizes how quantization-induced errors propagate and amplify over the rollout horizon. Unlike conventional PTQ methods, where sensitivity analysis is often coupled to the quantization procedure, TQS enables a priori sensitivity estimation decoupled from quantizer selection and bit-width assignment. This separation allows for quantization budget planning even for black-box or compiled networks with fused operators. Building on this, we present TQS-PTQ, a flexible mixed-precision framework that requires no calibration data or costly second-order approximations. Our experiments show that a dynamical-systems perspective provides a robust, high-performing pathway for low-precision deployment in resource-constrained settings.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 23 of its 40 references that are in the map. First posted on arXiv 11 Jun 2026.

Builds on

23 of 40 references.

References · 23

  1. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  2. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,919
  3. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  4. 2022SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Modelscited by 1,386
  5. 2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,298
  6. 2022LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scalecited by 906
  7. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 879
  8. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 815
  9. 2022FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operatorscited by 776
  10. 2023A decoder-only foundation model for time-series forecastingcited by 692
  11. 2020Up or Down? Adaptive Rounding for Post-Training Quantizationcited by 621
  12. 2022ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformerscited by 526
11 more
  1. 2023QuIP: 2-Bit Quantization of Large Language Models With Guaranteescited by 414
  2. 2019HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precisioncited by 402
  3. 2019HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networkscited by 261
  4. 2023Neural General Circulation Models for Weather and Climatecited by 239
  5. 2025GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric Calibrationcited by 60
  6. 2025Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantizationcited by 41
  7. 2022Hard-Constrained Deep Learning for Climate Downscalingcited by 32
  8. 2020On Lyapunov Exponents for RNNs: Understanding Information Propagation Using Dynamical Systems Toolscited by 31
  9. 2023Finite-time Lyapunov exponents of deep neural networkscited by 12
  10. 2025Identifying Sensitive Weights via Post-quantization Integralcited by 11
  11. 2025Mix-QViT: Mixed-Precision Vision Transformer Quantization Driven by Layer Importance and Quantization Sensitivitycited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Auditing Invisible Weight Updates with Reference Tracescited by 0
  2. 2026Calibration Bets on the Past: Post-Training Quantization for Financial Time-Series Forecastingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Q-PACE: Dynamic Precision Allocation for Quantization-Aware Training
  2. 2024Q-S5: Towards Quantized State Space Models
  3. 2026A Layer Importance Metric for Quantization Accounting for the Speed-Quality Trade-off in Autoregressive Models
  4. 2021In-Hindsight Quantization Range Estimation for Quantized Training
  5. 2021Data-free mixed-precision quantization using novel sensitivity metric
  6. 2026A Target-Centric Survey of Quantization-Aware Training
  7. 2025Beyond Outliers: A Study of Optimizers Under Quantization
  8. 2026RAMP: Robust Adaptive Mixed-Precision Quantization for Edge CPU Vision Models