paper-with-me

Papers

Sinusoidal Frequency Estimation by Gradient Descent

2022-10-26 · Ben Hayes, Charalampos Saitis, György Fazekas

Sinusoidal parameter estimation is a fundamental task in applications from spectral analysis to time-series forecasting. Estimating the sinusoidal frequency parameter by gradient descent is, however, often impossible as the error function is non-convex and densely populated with local minima. The growing family of differentiable signal processing methods has therefore been unable to tune the frequency of oscillatory components, preventing their use in a broad range of applications. This work presents a technique for joint sinusoidal frequency and amplitude estimation using the Wirtinger derivatives of a complex exponential surrogate and any first order gradient-based optimizer, enabling end to-end training of neural network controllers for unconstrained sinusoidal models.

📄 PDF Abstract BibTeX arXiv:2210.14476

Code (1)

ben-hayes/sinusoidal-gradient-descent 공식 구현 pytorch

Tasks

parameter estimationTime SeriesTime Series AnalysisTime Series Forecasting

Similar Papers 제목 키워드 기반

Gradient-Descent Based Optimization of Multi-Tone Sinusoidal Frequency Modulated Waveforms

2023-04-22 · David G. Felton, David A. Hague

This paper describes a gradient-descent based optimization algorithm for synthesizing Multi-Tone Sinusoidal Frequency Modulated (MTSFM) waveforms with low Auto-Correlation Function (ACF) sidelobes in a specified region o…

Computational Efficiency

Estimation Algorithm Non-Stationary Frequency of the Sinusoidal Signal

2021-09-20 · S. I. Nizovtsev, S. V. Shavetov, A. A. Pyrkin

The article considers the problem of identifying the variable frequency of a sinusoidal signal. To obtain a regression model of the signal, an iterative differentiation of the original analytical expression is performed,…

LEMMAregression

Learning in Sinusoidal Spaces with Physics-Informed Neural Networks

2021-09-20 · Jian Cheng Wong, Chinchun Ooi, Abhishek Gupta, Yew-Soon Ong

A physics-informed neural network (PINN) uses physics-augmented loss functions, e.g., incorporating the residual term from governing partial differential equations (PDEs), to ensure its output is consistent with fundamen…

WAVEQ: GRADIENT-BASED DEEP QUANTIZATION OF NEURAL NETWORKS THROUGH SINUSOIDAL REGULARIZATION

2021-01-01 · Ahmed T. Elthakeb, Prannoy Pilligundla, Tarek Elgindi, FatemehSadat Mireshghallah 외

Deep quantization of neural networks below eight bits can lead to superlinear benefits in storage and compute efficiency. However, homogeneously quantizing all the layers to the same level does not account for the distin…

Quantization

Understanding the Spectral Bias of Coordinate Based MLPs Via Training Dynamics

2023-01-14 · John Lazzari, Xiuwen Liu

Spectral bias is an important observation of neural network training, stating that the network will learn a low frequency representation of the target function before converging to higher frequency components. This prope…