Binned Spectral Power Loss for Improved Prediction of Chaotic Systems

• URL: http://arxiv.org/abs/2502.00472v1
• Date: Sat, 01 Feb 2025 15:58:21 GMT
• Title: Binned Spectral Power Loss for Improved Prediction of Chaotic Systems
• Authors: Dibyajyoti Chakraborty, Arvind T. Mohan, Romit Maulik,
• Abstract summary: We introduce a novel approach to mitigate the spectral bias which we call the Binned Spectral Power ( BSP) Loss.<n>Unlike traditional losses that focus on pointwise misfits, our BSP loss explicitly penalizes deviations in the energy distribution across different scales.<n>Our results demonstrate that the BSP loss significantly improves the stability and spectral accuracy of neural forecasting models.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Forecasting multiscale chaotic dynamical systems with deep learning remains a formidable challenge due to the spectral bias of neural networks, which hinders the accurate representation of fine-scale structures in long-term predictions. This issue is exacerbated when models are deployed autoregressively, leading to compounding errors and instability. In this work, we introduce a novel approach to mitigate the spectral bias which we call the Binned Spectral Power (BSP) Loss. The BSP loss is a frequency-domain loss function that adaptively weighs errors in predicting both larger and smaller scales of the dataset. Unlike traditional losses that focus on pointwise misfits, our BSP loss explicitly penalizes deviations in the energy distribution across different scales, promoting stable and physically consistent predictions. We demonstrate that the BSP loss mitigates the well-known problem of spectral bias in deep learning. We further validate our approach for the data-driven high-dimensional time-series forecasting of a range of benchmark chaotic systems which are typically intractable due to spectral bias. Our results demonstrate that the BSP loss significantly improves the stability and spectral accuracy of neural forecasting models without requiring architectural modifications. By directly targeting spectral consistency, our approach paves the way for more robust deep learning models for long-term forecasting of chaotic dynamical systems.

Related papers

• Spectral bias in physics-informed and operator learning: Analysis and mitigation guidelines [3.758814046658822]
  spectral bias is when low-frequency components of a solution are learned faster than high-frequency modes.<n>We show that spectral bias is not simply representational but fundamentally dynamical.<n>For neural operators, we show that spectral bias is dependent on the neural operator architecture.
  arXiv  Detail & Related papers  (2026-02-22T16:29:18Z)
• KoopGen: Koopman Generator Networks for Representing and Predicting Dynamical Systems with Continuous Spectra [65.11254608352982]
  We introduce a generator-based neural Koopman framework that models dynamics through a structured, state-dependent representation of Koopman generators.<n>By exploiting the intrinsic Cartesian decomposition into skew-adjoint and self-adjoint components, KoopGen separates conservative transport from irreversible dissipation.
  arXiv  Detail & Related papers  (2026-02-15T06:32:23Z)
• SynCast: Synergizing Contradictions in Precipitation Nowcasting via Diffusion Sequential Preference Optimization [62.958457694151384]
  We introduce preference optimization into precipitation nowcasting for the first time, motivated by the success of reinforcement learning from human feedback in large language models.<n>In the first stage, the framework focuses on reducing FAR, training the model to effectively suppress false alarms.
  arXiv  Detail & Related papers  (2025-10-22T16:11:22Z)
• A Unified Frequency Domain Decomposition Framework for Interpretable and Robust Time Series Forecasting [81.73338008264115]
  Current approaches for time series forecasting, whether in the time or frequency domain, predominantly use deep learning models based on linear layers or transformers.<n>We propose FIRE, a unified frequency domain decomposition framework that provides a mathematical abstraction for diverse types of time series.<n>Fire consistently outperforms state-of-the-art models on long-term forecasting benchmarks.
  arXiv  Detail & Related papers  (2025-10-11T09:59:25Z)
• Causal Graph Profiling via Structural Divergence for Robust Anomaly Detection in Cyber-Physical Systems [25.567981742631005]
  Causal Graph-based Anomaly Detection framework designed for reliable cyberattack detection in public infrastructure systems.<n>CGAD follows a two-phase supervised framework -- causal profiling and anomaly scoring.<n>By leveraging causal structures, CGAD achieves superior adaptability and accuracy in non-stationary and imbalanced time series environments.
  arXiv  Detail & Related papers  (2025-08-13T05:26:43Z)
• PnP-DA: Towards Principled Plug-and-Play Integration of Variational Data Assimilation and Generative Models [0.1052166918701117]
  Earth system modeling presents a fundamental challenge in scientific computing.<n>Even the most powerful AI- or physics-based forecast system suffer from gradual error accumulation.<n>We propose a Plug-and-Play algorithm that alternates a lightweight, gradient-based analysis update with a single forward pass through a pretrained prior conditioned on the background forecast.
  arXiv  Detail & Related papers  (2025-08-01T05:19:19Z)
• Turb-L1: Achieving Long-term Turbulence Tracing By Tackling Spectral Bias [43.0262112921538]
  We propose Turb-L1, an innovative turbulence prediction method.<n>It accurately captures cross-scale interactions and preserves the fidelity of high-frequency dynamics.<n>In long-term predictions, it reduces Mean Squared Error (MSE) by $80.3%$ and increases Structural Similarity (SSIM) by over $9times$ compared to the SOTA baseline.
  arXiv  Detail & Related papers  (2025-05-25T08:38:55Z)
• Model Hemorrhage and the Robustness Limits of Large Language Models [119.46442117681147]
  Large language models (LLMs) demonstrate strong performance across natural language processing tasks, yet undergo significant performance degradation when modified for deployment. We define this phenomenon as model hemorrhage - performance decline caused by parameter alterations and architectural changes.
  arXiv  Detail & Related papers  (2025-03-31T10:16:03Z)
• Topology-Aware Conformal Prediction for Stream Networks [54.505880918607296]
  We propose Spatio-Temporal Adaptive Conformal Inference (textttCISTA), a novel framework that integrates network topology and temporal dynamics into the conformal prediction framework.<n>Our results show that textttCISTA effectively balances prediction efficiency and coverage, outperforming existing conformal prediction methods for stream networks.
  arXiv  Detail & Related papers  (2025-03-06T21:21:15Z)
• Error-quantified Conformal Inference for Time Series [55.11926160774831]
  Uncertainty quantification in time series prediction is challenging due to the temporal dependence and distribution shift on sequential data.<n>We propose itError-quantified Conformal Inference (ECI) by smoothing the quantile loss function.<n>ECI can achieve valid miscoverage control and output tighter prediction sets than other baselines.
  arXiv  Detail & Related papers  (2025-02-02T15:02:36Z)
• The Power of Perturbation under Sampling in Solving Extensive-Form Games [56.013335390600524]
  This paper investigates how perturbation does and does not improve the Follow-the-Regularized-Leader (FTRL) algorithm in imperfect-information extensive-form games.<n>Perturbing the expected payoffs guarantees that the FTRL dynamics reach an approximate equilibrium.<n>We show that in the last-iterate sense, the FTRL consistently outperforms the non-samplinged FTRL.
  arXiv  Detail & Related papers  (2025-01-28T00:29:38Z)
• Transformer-Based Bearing Fault Detection using Temporal Decomposition Attention Mechanism [0.40964539027092917]
  Bearing fault detection is a critical task in predictive maintenance, where accurate and timely fault identification can prevent costly downtime and equipment damage.<n>Traditional attention mechanisms in Transformer neural networks often struggle to capture the complex temporal patterns in bearing vibration data, leading to suboptimal performance.<n>We propose a novel attention mechanism, Temporal Decomposition Attention (TDA), which combines temporal bias encoding with seasonal-trend decomposition to capture both long-term dependencies and periodic fluctuations in time series data.
  arXiv  Detail & Related papers  (2024-12-15T16:51:31Z)
• Harnessing Loss Decomposition for Long-Horizon Wave Predictions via Deep Neural Networks [0.0]
  We propose a novel loss decomposition strategy that breaks down the loss into separate phase and amplitude components.<n>This technique improves the long-term prediction accuracy of neural networks in wave propagation tasks by explicitly accounting for numerical errors.
  arXiv  Detail & Related papers  (2024-12-04T00:27:54Z)
• Long-Term Prediction Accuracy Improvement of Data-Driven Medium-Range Global Weather Forecast [5.284452133959932]
  A universal neural operator called the Spherical Harmonic Neural Operator (SHNO) is introduced to improve long-term iterative forecasts. SHNO uses the spherical harmonic basis to mitigate distortions for spherical data and uses gated residual spectral attention (GRSA) to correct spectral bias caused by spurious correlations across different scales. Our findings highlight the benefits and potential of SHNO to improve the accuracy of long-term prediction.
  arXiv  Detail & Related papers  (2024-06-26T02:06:27Z)
• Unmasking Bias in Diffusion Model Training [40.90066994983719]
  Denoising diffusion models have emerged as a dominant approach for image generation. They still suffer from slow convergence in training and color shift issues in sampling. In this paper, we identify that these obstacles can be largely attributed to bias and suboptimality inherent in the default training paradigm.
  arXiv  Detail & Related papers  (2023-10-12T16:04:41Z)
• Momentum Diminishes the Effect of Spectral Bias in Physics-Informed Neural Networks [72.09574528342732]
  Physics-informed neural network (PINN) algorithms have shown promising results in solving a wide range of problems involving partial differential equations (PDEs) They often fail to converge to desirable solutions when the target function contains high-frequency features, due to a phenomenon known as spectral bias. In the present work, we exploit neural tangent kernels (NTKs) to investigate the training dynamics of PINNs evolving under gradient descent with momentum (SGDM)
  arXiv  Detail & Related papers  (2022-06-29T19:03:10Z)
• Probabilistic AutoRegressive Neural Networks for Accurate Long-range Forecasting [6.295157260756792]
  We introduce the Probabilistic AutoRegressive Neural Networks (PARNN) PARNN is capable of handling complex time series data exhibiting non-stationarity, nonlinearity, non-seasonality, long-range dependence, and chaotic patterns. We evaluate the performance of PARNN against standard statistical, machine learning, and deep learning models, including Transformers, NBeats, and DeepAR.
  arXiv  Detail & Related papers  (2022-04-01T17:57:36Z)
• Bayesian Spillover Graphs for Dynamic Networks [5.77019633619109]
  We present a novel method for learning temporal relationships, identifying critical nodes, and quantifying uncertainty for multi-horizon spillover effects. We show significant performance gains against state-of-the-art Bayesian Networks and deep-learning baselines. Applications to real-world systems also showcase BSG as an exploratory analysis tool for uncovering indirect spillovers and quantifying risk.
  arXiv  Detail & Related papers  (2022-03-03T18:42:43Z)
• On the Generalization of Stochastic Gradient Descent with Momentum [58.900860437254885]
  We first show that there exists a convex loss function for which algorithmic stability fails to establish generalization guarantees. For smooth Lipschitz loss functions, we analyze a modified momentum-based update rule, and show that it admits an upper-bound on the generalization error. For the special case of strongly convex loss functions, we find a range of momentum such that multiple epochs of standard SGDM, as a special form of SGDEM, also generalizes.
  arXiv  Detail & Related papers  (2021-02-26T18:58:29Z)
• Stochastically forced ensemble dynamic mode decomposition for forecasting and analysis of near-periodic systems [65.44033635330604]
  We introduce a novel load forecasting method in which observed dynamics are modeled as a forced linear system. We show that its use of intrinsic linear dynamics offers a number of desirable properties in terms of interpretability and parsimony. Results are presented for a test case using load data from an electrical grid.
  arXiv  Detail & Related papers  (2020-10-08T20:25:52Z)
• On the Generalization of Stochastic Gradient Descent with Momentum [84.54924994010703]
  momentum-based accelerated variants of gradient descent (SGD) are widely used when training machine learning models. We first show that there exists a convex loss function for which the stability gap for multiple epochs of SGD with standard heavy-ball momentum (SGDM) becomes unbounded. For smooth Lipschitz loss functions, we analyze a modified momentum-based update rule, i.e., SGD with early momentum (SGDEM) under a broad range of step-sizes.
  arXiv  Detail & Related papers  (2018-09-12T17:02:08Z)

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.