A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
New transforms improve signal classification and data analysis.
In many state-of-the-art compression systems, signal transformation is an integral part of the encoding and decoding process, where transforms provide compact representations for the signals of interest. This paper introduces a class of transforms called graph-based transforms (GBTs) for video compression, and proposes…
New theory explains signal propagation in normalization-free transformers.
A new model classifies lightning signals more accurately across different scales.
Simplified Butterfly-Net2 improves CNN efficiency in solving PDEs and signal processing tasks.
Improved signal classification using multiple wavelets and their smooth coefficients.
Many signals on Cartesian product graphs appear in the real world, such as digital images, sensor observation time series, and movie ratings on Netflix. These signals are "multi-dimensional" and have directional characteristics along each factor graph. However, the existing graph Fourier transform does not distinguish …
MODWST improves classification tasks with wavelet scattering.
Deep vanilla transformers trained without shortcuts achieve similar performance to standard models.
Effective theory for Transformer initialization improves model performance.
We study the property of the Fused Lasso Signal Approximator (FLSA) for estimating a blocky signal sequence with additive noise. We transform the FLSA to an ordinary Lasso problem. By studying the property of the design matrix in the transformed Lasso problem, we find that the irrepresentable condition might not hold, …
Computing accurate estimates of the Fourier transform of analog signals from discrete data points is important in many fields of science and engineering. The conventional approach of performing the discrete Fourier transform of the data implicitly assumes periodicity and bandlimitedness of the signal. In this paper, we…
DPI quantifies phase differences in 1D and multidimensional signals using Riesz transform.
HFformer outperforms LSTM in high-frequency trading with multiple signals.
Method extracts features from signals for classification with explainability.
We present a signal representation framework called the sparse manifold transform that combines key ideas from sparse coding, manifold learning, and slow feature analysis. It turns non-linear transformations in the primary sensory signal space into linear interpolations in a representational embedding space while maint…
Improves signal detection in non-Gaussian noise using transformed data.
The wavelet scattering transform is an invariant signal representation suitable for many signal processing and machine learning applications. We present the Kymatio software package, an easy-to-use, high-performance Python implementation of the scattering transform in 1D, 2D, and 3D that is compatible with modern deep …
RP-GFRFT unifies fractional order and rotation control for graph signals.
This study proposes a trainable adaptive window switching (AWS) method and apply it to a deep-neural-network (DNN) for speech enhancement in the modified discrete cosine transform domain. Time-frequency (T-F) mask processing in the short-time Fourier transform (STFT)-domain is a typical speech enhancement method. To re…
While deep learning has received a surge of interest in a variety of fields in recent years, major deep learning models barely use complex numbers. However, speech, signal and audio data are naturally complex-valued after Fourier Transform, and studies have shown a potentially richer representation of complex nets. In …
Improves detection of low-rank signals from noisy data matrices.
Signals are geometric submanifolds with specific properties.
In the design of brain-computer interface systems, classification of Electroencephalogram (EEG) signals is the essential part and a challenging task. Recently, as the marginalized discrete wavelet transform (mDWT) representations can reveal features related to the transient nature of the EEG signals, the mDWT coefficie…
We propose a simple and efficient time-series clustering framework particularly suited for low Signal-to-Noise Ratio (SNR), by simultaneous smoothing and dimensionality reduction aimed at preserving clustering information. We extend the sparse K-means algorithm by incorporating structured sparsity, and use it to exploi…
Transformer model predicts train axle vibrations for safer maintenance.
A new iterative low complexity algorithm has been presented for computing the Walsh-Hadamard transform (WHT) of an dimensional signal with a -sparse WHT, where is a power of two and , scales sub-linearly in for some . Assuming a random support model for the non-zero transform domain…
We give a new algorithm for approximating the Discrete Fourier transform of an approximately sparse signal that has been corrupted by worst-case noise, namely a bounded number of coordinates of the signal have been corrupted arbitrarily. Our techniques generalize to a wide range of linear transformations that are…
Wi-GATr learns to simulate wireless signals with high accuracy and speed.
In this paper we develop a novel computational sensing framework for sensing and recovering structured signals. When trained on a set of representative signals, our framework learns to take undersampled measurements and recover signals from them using a deep convolutional neural network. In other words, it learns a tra…
The paper detects changes in graph signal means offline.
We study the first-order scattering transform as a candidate for reducing the signal processed by a convolutional neural network (CNN). We show theoretical and empirical evidence that in the case of natural images and sufficiently small translation invariance, this transform preserves most of the signal information nee…
This paper enhances language models with knowledge awareness.
Generative networks have made it possible to generate meaningful signals such as images and texts from simple noise. Recently, generative methods based on GAN and VAE were developed for graphs and graph signals. However, the mathematical properties of these methods are unclear, and training good generative models is di…
We propose a new class of transforms that we call {\it Lehmer Transform} which is motivated by the {\it Lehmer mean function}. The proposed {\it Lehmer transform} decomposes a function of a sample into their constituting statistical moments. Theoretical properties of the proposed transform are presented. This transform…
The study recovers airflow from thoracic and abdominal movements using advanced signal processing.
Many applications in signal processing benefit from the sparsity of signals in a certain transform domain or dictionary. Synthesis sparsifying dictionaries that are directly adapted to data have been popular in applications such as image denoising, inpainting, and medical image reconstruction. In this work, we focus in…
Paper introduces rational Gaussian wavelets for efficient signal approximation.
Self-supervised ECG learning improves emotion recognition.
Many problems in image processing and computer vision (e.g. colorization, style transfer) can be posed as 'manipulating' an input image into a corresponding output image given a user-specified guiding signal. A holy-grail solution towards generic image manipulation should be able to efficiently alter an input image wit…
Deep learning models predict epileptic seizures with high accuracy.
The Weyl transform is introduced as a rich framework for data representation. Transform coefficients are connected to the Walsh-Hadamard transform of multiscale autocorrelations, and different forms of dyadic periodicity in a signal are shown to appear as different features in its Weyl coefficients. The Weyl transform …
Study on signal-plus-noise decomposition in nonlinear spiked random matrices.
New methods implement manifold scattering transform for high-dimensional point cloud data.
New neural network extracts signal components and their IFs from non-uniform samples.
Paper proposes integrating wavelet transform, channel attention, and LSTM for better stock price prediction.
Graph signal processing detects hallucinations in large language models.
New method denoises graph signals using wavelets, scalable for large graphs.