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.
A guide to using low-pass graph filters for network data.
We propose a Bayesian nonparametric method for low-pass filtering that can naturally handle unevenly-sampled and noise-corrupted observations. The proposed model is constructed as a latent-factor model for time series, where the latent factors are Gaussian processes with non-overlapping spectra. With this construction,…
The MAXFLAT low-pass filter improves factor adjustment for better portfolio performance in China's stock market.
DOPPLER optimizes DP training with low-pass filtering, improving model accuracy.
Study assesses deep neural networks' robustness in mammogram images.
Graph neural networks have become one of the most important techniques to solve machine learning problems on graph-structured data. Recent work on vertex classification proposed deep and distributed learning models to achieve high performance and scalability. However, we find that the feature vectors of benchmark datas…
We study the nature of fluctuations in variety of price indices involving companies listed on the New York Stock Exchange. The fluctuations at multiple scales are extracted through the use of wavelets belonging to Daubechies basis. The fact that these basis sets satisfy vanishing moments conditions makes them ideal to …
GCN improved for large graphs with LCF to reduce complexity and noise.
Paper develops an online EM algorithm for graph signal inference from streaming data.
Robust ASR model removes fast-changing features to resist attacks.
This work analyzes the stability of graph filters under large perturbations.
Fourier methods have a long and proven track record as an excellent tool in data processing. As memory and computational constraints gain importance in embedded and mobile applications, we propose to combine Fourier methods and recurrent neural network architectures. The short-time Fourier transform allows us to effici…
Method detects new physics signals without prior knowledge.
New -Laplacian GNN model tackles heterophilic graphs by improving node classification.
Recently, the field of adversarial machine learning has been garnering attention by showing that state-of-the-art deep neural networks are vulnerable to adversarial examples, stemming from small perturbations being added to the input image. Adversarial examples are generated by a malicious adversary by obtaining access…
We perform wavelet decomposition of high frequency financial time series into large and small time scale components. Taking the FTSE100 index as a case study, and working with the Haar basis, it turns out that the small scale component defined by most ( 99.6%) of the wavelet coefficients can be neglected for th…
A simple method for estimating PMF on large supports, preserving structure and suppressing noise.
In this paper we propose the use of continuous residual modules for graph kernels in Graph Neural Networks. We show how both discrete and continuous residual layers allow for more robust training, being that continuous residual layers are those which are applied by integrating through an Ordinary Differential Equation …
Graph Convolutional Networks (GCNs) and their variants have experienced significant attention and have become the de facto methods for learning graph representations. GCNs derive inspiration primarily from recent deep learning approaches, and as a result, may inherit unnecessary complexity and redundant computation. In…
A new method for joint noise removal and trend estimation from sparse signals.
We study the effectiveness of various approaches that defend against adversarial attacks on deep networks via manipulations based on basis function representations of images. Specifically, we experiment with low-pass filtering, PCA, JPEG compression, low resolution wavelet approximation, and soft-thresholding. We evalu…
We propose a Fourier-based learning algorithm for highly nonlinear multiclass classification. The algorithm is based on a smoothing technique to calculate the probability distribution of all classes. To obtain the probability distribution, the density distribution of each class is smoothed by a low-pass filter separate…
Reinforcement learning (RL) agents performing complex tasks must be able to remember observations and actions across sizable time intervals. This is especially true during the initial learning stages, when exploratory behaviour can increase the delay between specific actions and their effects. Many new or popular appro…
This paper considers a new framework to detect communities in a graph from the observation of signals at its nodes. We model the observed signals as noisy outputs of an unknown network process, represented as a graph filter that is excited by a set of unknown low-rank inputs/excitations. Application scenarios of this m…
Seminal works on graph neural networks have primarily targeted semi-supervised node classification problems with few observed labels and high-dimensional signals. With the development of graph networks, this setup has become a de facto benchmark for a significant body of research. Interestingly, several works have rece…
Graph neural networks improve network localization accuracy and efficiency.
Time-continuous dimensional descriptions of emotions (e.g., arousal, valence) allow researchers to characterize short-time changes and to capture long-term trends in emotion expression. However, continuous emotion labels are generally not synchronized with the input speech signal due to delays caused by reaction-time, …
Filter banks are a popular tool for the analysis of piecewise smooth signals such as natural images. Motivated by the empirically observed properties of scale and detail coefficients of images in the wavelet domain, we propose a hierarchical deep generative model of piecewise smooth signals that is a recursion across s…
Introduces Spectral Attention for better long-range time series forecasting.
Improved image restoration using frequency-guided sampling.
Proposes a new method to improve CNNs' shift invariance and accuracy.
Graph-based methods have been demonstrated as one of the most effective approaches for semi-supervised learning, as they can exploit the connectivity patterns between labeled and unlabeled data samples to improve learning performance. However, existing graph-based methods either are limited in their ability to jointly …
BankGCN improves graph convolution networks by handling multi-channel signals with adaptive filter banks.
Data coarse graining improves model performance by filtering out less relevant features.
A new hybrid GNN framework tackles oversmoothing in graph data.
New method improves image denoising with fewer parameters and less data.
Convolutional Neural Networks (CNNs) have shown impressive performance in computer vision tasks such as image classification, detection, and segmentation. Moreover, recent work in Generative Adversarial Networks (GANs) has highlighted the importance of learning by progressively increasing the difficulty of a learning t…
AGE improves graph embedding by smoothing features and iteratively enhancing node embeddings.
This paper examines how Higher-Order Langevin Dynamics reduces memorization in diffusion models.
Graph convolutions can enhance high frequencies, leading to over-sharpening.
AaSP improves audio self-supervised learning by addressing aliasing issues.
MAGNA improves graph neural networks by incorporating multi-hop context information.
Develops method for learning signed graphs from smooth signals.
FRA-Attack improves adversarial transferability for closed-source MLLMs by aligning visual focus across models.
Recursive training of generative models can lead to model collapse, and the recursion converges to a unique limiting distribution.
SCE improves network embedding using sparsest cut for negative samples only.
Effective and powerful methods for denoising real electrocardiogram (ECG) signals are important for wearable sensors and devices. Deep Learning (DL) models have been used extensively in image processing and other domains with great success but only very recently have been used in processing ECG signals. This paper pres…
TREK uses distillation to help students solve hard problems.