Quantizing Time-Series Models As Dynamical Systems: Trajectory-Based Quantization Sensitivity Score
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Liquid Time-constant Networks
We introduce a new class of time-continuous recurrent neural network models. Instead of declaring a learning system's dynamics by implicit nonlinearities, we construct networks of linear first-order dynamical systems mod…
Time SeriesTime Series AnalysisTime Series PredictionReconstructing a dynamical system and forecasting time series by self-consistent deep learning
We introduce a self-consistent deep-learning framework which, for a noisy deterministic time series, provides unsupervised filtering, state-space reconstruction, identification of the underlying differential equations an…
Time SeriesTime Series AnalysisTempoGPT: Enhancing Temporal Reasoning via Quantizing Embedding
Multi-modal language model has made advanced progress in vision and audio, but still faces significant challenges in dealing with complex reasoning tasks in the time series domain. The reasons are twofold. First, labels …
Language ModelingLanguage ModellingTime SeriesContext parroting: A simple but tough-to-beat baseline for foundation models in scientific machine learning
Recently-developed time series foundation models for scientific machine learning exhibit emergent abilities to predict physical systems. These abilities include zero-shot forecasting, in which a model forecasts future st…
In-Context LearningTime SeriesTime Series ForecastingSafe Active Learning for Time-Series Modeling with Gaussian Processes
Learning time-series models is useful for many applications, such as simulation and forecasting. In this study, we consider the problem of actively learning time-series models while taking given safety constraints into a…
Active LearningGaussian ProcessesTime Series