Time-warping estimation via stationarity-based learning of the de-warped signal

• URL: http://arxiv.org/abs/2609.16796v1
• Date: Tue, 15 Sep 2026 08:02:58 GMT
• Title: Time-warping estimation via stationarity-based learning of the de-warped signal
• Abstract summary: Time-warping estimation is a fundamental problem in signal processing with applications in bioacoustics, radar, and biomedical analysis.<n>This paper introduces a Time-Warping Estimation Trainable (TWET) model for estimating timewarping functions from a single observation.
• Score: 0.8594140167290095
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Time-warping estimation is a fundamental problem in signal processing with applications in bioacoustics, radar, and biomedical analysis. This paper introduces a Time-Warping Estimation Trainable (TWET) model for estimating timewarping functions from a single observation. The proposed approach formulates time-warping estimation as a stationarization problem in the wavelet domain and leverages a hierarchical dilated convolutional architecture to estimate the time-warping functions. A differentiable stationarity criterion is introduced for end-to-end optimization. TWET is compared with existing approaches. Experimental results show improved deformation reconstruction accuracy together with significantly reduced computation time, making the framework compatible with low-latency applications.

Related papers

• From Atoms to Entropy: Optimal Noise Allocation for Diffusion Training in the Convex Regime [52.459513910242485]
  We develop a general statistical framework for studying optimal noise-level allocation in diffusion training.<n>We show that the optimized training schedule admits an atomic minimizer, concentrated on finitely many noise levels.<n>We then evaluate the entropic schedule in larger-scale experiments, where full schedule optimization is currently intractable.
  arXiv  Detail & Related papers  (2026-07-10T20:59:06Z)
• Temporal Structure Matters for Efficient Test-Time Adaptation in Wearable Human Activity Recognition [0.20391237204597365]
  Test-time adaptation (TTA) mitigates performance degradation under real-world cross-user distribution shifts.<n>Existing methods largely inherit assumptions from vision tasks and underexploit the inherent inter-window temporal structure in WHAR streams.<n>We propose SIGHT, a lightweight and backpropagation-free TTA framework for WHAR, enabling real-time edge deployment.
  arXiv  Detail & Related papers  (2026-05-06T08:06:27Z)
• Predictor-Based Output-Feedback Control of Linear Systems with Time-Varying Input and Measurement Delays via Neural-Approximated Prediction Horizons [6.093618731228799]
  We develop an output-feedback predictor design for systems with delays in both the input and the measurement.<n>We prove that the resulting closed-loop system is globally exponentially stable when the prediction horizon is approximated with sufficiently small error.
  arXiv  Detail & Related papers  (2026-03-31T01:09:24Z)
• Direct Interval Propagation Methods using Neural-Network Surrogates for Uncertainty Quantification in Physical Systems Surrogate Model [8.373469792572356]
  In engineering, uncertainty propagation aims to characterise system outputs under uncertain inputs.<n>Standard interval propagation relies on solving optimisation problems that become computationally expensive for complex systems.<n>We reformulate interval propagation as an interval-valued regression problem that directly predicts output bounds.
  arXiv  Detail & Related papers  (2026-03-22T16:25:43Z)
• Statistical benchmarking of transformer models in low signal-to-noise time-series forecasting [0.0]
  We show that two-way attention transformers, which alternate between temporal and cross-sectional self-attention, can outperform standard baselines.<n>We also introduce a dynamic sparsification procedure for attention matrices applied during training, and demonstrate that it becomes significantly effective in noisy environments.
  arXiv  Detail & Related papers  (2026-02-10T15:13:57Z)
• Efficient Convolutional Forward Model for Passive Acoustic Mapping and Temporal Monitoring [4.219150964619931]
  We introduce a PAM beamforming framework based on a convolutional formulation in the time domain.<n>In this framework, PAM is formulated as an inverse problem in which the forward operator maps cavitation activity to recorded radio-frequency signals.<n>We then formulate a regularized inversion that incorporates prior knowledge on cavitation activity.
  arXiv  Detail & Related papers  (2026-01-12T09:32:26Z)
• Multiresolution Analysis and Statistical Thresholding on Dynamic Networks [49.09073800467438]
  ANIE (Adaptive Network Intensity Estimation) is a multi-resolution framework designed to automatically identify the time scales at which network structure evolves.<n>We show that ANIE adapts to the appropriate time resolution and is able to capture sharp structural changes while remaining robust to noise.
  arXiv  Detail & Related papers  (2025-06-01T22:55:55Z)
• Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximation [62.969796245827006]
  Delayed-PSVI is an optimistic value-based algorithm that explores the value function space via noise perturbation with posterior sampling. We show our algorithm achieves $widetildeO(sqrtd3H3 T + d2H2 E[tau]$ worst-case regret in the presence of unknown delays. We incorporate a gradient-based approximate sampling scheme via Langevin dynamics for Delayed-LPSVI.
  arXiv  Detail & Related papers  (2023-10-29T06:12:43Z)
• USTEP: Spatio-Temporal Predictive Learning under A Unified View [62.58464029270846]
  We introduce USTEP (Unified S-TEmporal Predictive learning), an innovative framework that reconciles the recurrent-based and recurrent-free methods by integrating both micro-temporal and macro-temporal scales.
  arXiv  Detail & Related papers  (2023-10-09T16:17:42Z)
• Efficient Estimation for Longitudinal Networks via Adaptive Merging [21.62069959992736]
  We propose an efficient estimation framework for longitudinal network, leveraging strengths of adaptive network merging, tensor decomposition and point process. It merges neighboring sparse networks so as to enlarge the number of observed edges and reduce estimation variance. A projected descent algorithm is proposed to facilitate estimation, where upper bound of the estimation error in each iteration is established.
  arXiv  Detail & Related papers  (2022-11-15T03:17:11Z)
• Supporting Optimal Phase Space Reconstructions Using Neural Network Architecture for Time Series Modeling [68.8204255655161]
  We propose an artificial neural network with a mechanism to implicitly learn the phase spaces properties. Our approach is either as competitive as or better than most state-of-the-art strategies.
  arXiv  Detail & Related papers  (2020-06-19T21:04:47Z)
• A Generative Learning Approach for Spatio-temporal Modeling in Connected Vehicular Network [55.852401381113786]
  This paper proposes LaMI (Latency Model Inpainting), a novel framework to generate a comprehensive-temporal quality framework for wireless access latency of connected vehicles. LaMI adopts the idea from image inpainting and synthesizing and can reconstruct the missing latency samples by a two-step procedure. In particular, it first discovers the spatial correlation between samples collected in various regions using a patching-based approach and then feeds the original and highly correlated samples into a Varienational Autocoder (VAE)
  arXiv  Detail & Related papers  (2020-03-16T03:43:59Z)

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.