arXiv research

Locally adaptive clustering for tree delineation.

EvoMSN tackles time series forecasting under distribution shifts by evolving multi-scale normalization.

Neural HMM with AGA captures multi-scale dynamics in financial markets.

This work bridges two views of feature learning in neural networks.

CAST improves spectral clustering for multi-scale data by integrating reachability similarity.

WALNUTS improves sampling efficiency and robustness for multi-scale distributions.

Recently, Convolution Neural Networks (CNNs) obtained huge success in numerous vision tasks. In particular, DenseNets have demonstrated that feature reuse via dense skip connections can effectively alleviate the difficulty of training very deep networks and that reusing features generated by the initial layers in all s…

Novel neural network solves PDEs with multi-scale resolution.

This study presents a new lossy image compression method that utilizes the multi-scale features of natural images. Our model consists of two networks: multi-scale lossy autoencoder and parallel multi-scale lossless coder. The multi-scale lossy autoencoder extracts the multi-scale image features to quantized variables a…

Paper improves multi-step chord prediction in jazz music.

Tensor network architecture for classification and regression using wavelet transformations.

Modern audio source separation techniques rely on optimizing sequence model architectures such as, 1D-CNNs, on mixture recordings to generalize well to unseen mixtures. Specifically, recent focus is on time-domain based architectures such as Wave-U-Net which exploit temporal context by extracting multi-scale features. …

Paper introduces multi-scale methods to improve CATE estimation from EO data.

Proposes MscaleDNN for solving high-dimensional PDEs efficiently.

Boosting theory explains why multi-scale GNNs work.

Develops deep jump learning for continuous treatment OPE.

Convolutional Neural Network (CNN) has demonstrated impressive ability to represent hyperspectral images and to achieve promising results in hyperspectral image classification. However, traditional CNN models can only operate convolution on regular square image regions with fixed size and weights, so they cannot univer…

The analysis of temporal networks has a wide area of applications in a world of technological advances. An important aspect of temporal network analysis is the discovery of community structures. Real data networks are often very large and the communities are observed to have a hierarchical structure referred to as mult…

New algorithm reduces dynamic regret without prior function change knowledge.

Embed nodes with multi-scale attributes for robust network analysis.

Framework for multi-scale clustering using phase transitions.

Improved online algorithm for convex losses with near-optimal swap regret.

While Generative Adversarial Networks (GANs) have seen huge successes in image synthesis tasks, they are notoriously difficult to adapt to different datasets, in part due to instability during training and sensitivity to hyperparameters. One commonly accepted reason for this instability is that gradients passing from t…

Graph-based weather prediction adapted for local models.

New PINN architectures learn high-frequency features using Fourier features.

Compactifies moduli spaces of abelian differentials with specific zeroes and poles.

Proposes OC4Seq for detecting anomalies in discrete event sequences.

Paper tackles leverage effect estimation from noisy data.

New method improves robustness of large models without sacrificing accuracy.

Deep generative modeling using flows has gained popularity owing to the tractable exact log-likelihood estimation with efficient training and synthesis process. However, flow models suffer from the challenge of having high dimensional latent space, the same in dimension as the input space. An effective solution to the …

DRFormer uses dynamic tokenization and multi-scale transformer to forecast long time series.

We construct a new map from a convex function to a distribution on its domain, with the property that this distribution is a multi-scale exploration of the function. We use this map to solve a decade-old open problem in adversarial bandit convex optimization by showing that the minimax regret for this problem is $\tild…

MRC-LSTM predicts Bitcoin prices using CNN and LSTM.

CrossAD detects anomalies in time series data by considering cross-scale associations and cross-window modeling.

Novel framework for systemic risk analysis in financial markets.

This paper reviews some of the phenomenological models which have been introduced to incorporate the scaling properties of financial data. It also illustrates a microscopic model, based on heterogeneous interacting agents, which provides a possible explanation for the complex dynamics of markets' returns. Scaling and m…

Space2Vec learns multi-scale spatial representations from grid cell insights.

Inspired by coarse-graining approaches used in physics, we show how similar algorithms can be adapted for data. The resulting algorithms are based on layered tree tensor networks and scale linearly with both the dimension of the input and the training set size. Computing most of the layers with an unsupervised algorith…

Federated learning improves CRC grading accuracy and privacy.

MCFNet recovers spatial detail and fuses it with semantic information for real-time segmentation.

CViT learns complex physical systems using vision transformer techniques.

Langevin Dynamics speeds up mixing time with manifold hypothesis and multi-scale approach.

CRAUM-Net improves salient object detection with context and uncertainty modeling.

Improves speaker verification for variable-duration utterances using a feature pyramid module.

Model for directed synthesis of audio textures using multi-scale RNNs.

Improved recurrent neural networks learn long-term dependencies through multi-scale memory.

Proposes MSTD-RCNN for improved financial time-series classification.

Study abelian varieties' Weil-Petersson metric asymptotics.