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

• URL: http://arxiv.org/abs/2606.13300v3
• Date: Mon, 15 Jun 2026 10:44:03 GMT
• Title: Quantizing Time-Series Models As Dynamical Systems: Trajectory-Based Quantization Sensitivity Score
• Abstract summary: Trajectory-based Quantization Sensitivity Score (TQS) is a metric that reframes post-training quantization (PTQ) through the lens of dynamical-systems stability.<n>We present TQS-PTQ, a flexible mixed-precision framework that requires no calibration data or costly second-order approximations.<n>Our experiments show that a dynamical-systems perspective provides a robust, high-performing pathway for low-precision deployment in resource-constrained settings.
• Score: 11.59520862669959
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• Continual Quantum Architecture Search with Tensor-Train Encoding: Theory and Applications to Signal Processing [68.35481158940401]
  CL-QAS is a continual quantum architecture search framework.<n>It mitigates challenges of costly encoding amplitude and forgetting in variational quantum circuits.<n>It achieves controllable robustness expressivity, sample-efficient generalization, and smooth convergence without barren plateaus.
  arXiv  Detail & Related papers  (2026-01-10T02:36:03Z)
• FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix Approximation [55.12070409045766]
  Post-training quantization (PTQ) has stood out as a cost-effective and promising model compression paradigm in recent years.<n>Current PTQ methods for Vision Transformers (ViTs) still suffer from significant accuracy degradation, especially under low-bit quantization.
  arXiv  Detail & Related papers  (2025-06-13T07:57:38Z)
• Deep Unfolding with Kernel-based Quantization in MIMO Detection [26.033613526407226]
  This paper proposes a novel kernel-based adaptive quantization (KAQ) framework for deep unfolding networks.<n>The accuracy of proposed KAQ framework outperforms traditional methods and successfully reduces the model's inference latency.
  arXiv  Detail & Related papers  (2025-05-19T05:50:24Z)
• Universal Approximation Theorem of Deep Q-Networks [2.1756081703276]
  We analyze Deep Q-Networks (DQNs) via control and Forward-Backward Differential Equations (FBSDEs)<n>We show that DQNs can approximate the optimal Q-function on compact sets with arbitrary accuracy and high probability.<n>This work bridges deep reinforcement learning and control, offering insights into DQNs in continuous-time settings.
  arXiv  Detail & Related papers  (2025-05-04T22:57:33Z)
• Pointer Networks with Q-Learning for Combinatorial Optimization [55.2480439325792]
  We introduce the Pointer Q-Network (PQN), a hybrid neural architecture that integrates model-free Q-value policy approximation with Pointer Networks (Ptr-Nets) Our empirical results demonstrate the efficacy of this approach, also testing the model in unstable environments.
  arXiv  Detail & Related papers  (2023-11-05T12:03:58Z)
• A Study of Quantisation-aware Training on Time Series Transformer Models for Resource-constrained FPGAs [19.835810073852244]
  This study explores the quantisation-aware training (QAT) on time series Transformer models. We propose a novel adaptive quantisation scheme that dynamically selects between symmetric and asymmetric schemes during the QAT phase.
  arXiv  Detail & Related papers  (2023-10-04T08:25:03Z)
• Machine Learning Aided Dimensionality Reduction towards a Resource Efficient Projective Quantum Eigensolver [0.0]
  Recently developed Projective Quantum Eigensolver (PQE) has been demonstrated as an elegant methodology to compute the ground state energy of molecular systems. We have exploited the collective interplay of these two sets of parameters via machine learning techniques to bring out the synergistic inter-relationship.
  arXiv  Detail & Related papers  (2023-03-20T16:49:56Z)
• CSQ: Growing Mixed-Precision Quantization Scheme with Bi-level Continuous Sparsification [51.81850995661478]
  Mixed-precision quantization has been widely applied on deep neural networks (DNNs) Previous attempts on bit-level regularization and pruning-based dynamic precision adjustment during training suffer from noisy gradients and unstable convergence. We propose Continuous Sparsification Quantization (CSQ), a bit-level training method to search for mixed-precision quantization schemes with improved stability.
  arXiv  Detail & Related papers  (2022-12-06T05:44:21Z)
• Formal Controller Synthesis for Markov Jump Linear Systems with Uncertain Dynamics [64.72260320446158]
  We propose a method for synthesising controllers for Markov jump linear systems. Our method is based on a finite-state abstraction that captures both the discrete (mode-jumping) and continuous (stochastic linear) behaviour of the MJLS. We apply our method to multiple realistic benchmark problems, in particular, a temperature control and an aerial vehicle delivery problem.
  arXiv  Detail & Related papers  (2022-12-01T17:36:30Z)
• Green, Quantized Federated Learning over Wireless Networks: An Energy-Efficient Design [68.86220939532373]
  The finite precision level is captured through the use of quantized neural networks (QNNs) that quantize weights and activations in fixed-precision format. The proposed FL framework can reduce energy consumption until convergence by up to 70% compared to a baseline FL algorithm.
  arXiv  Detail & Related papers  (2022-07-19T16:37:24Z)
• NIPQ: Noise proxy-based Integrated Pseudo-Quantization [9.207644534257543]
  Straight-through estimator (STE) incurs unstable convergence during quantization-aware training (QAT) We propose a novel noise proxy-based integrated pseudoquantization (NIPQ) that enables unified support of pseudoquantization for both activation and weight. NIPQ outperforms existing quantization algorithms in various vision and language applications by a large margin.
  arXiv  Detail & Related papers  (2022-06-02T01:17:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.