arXiv research

Gradient descent trains shallow neural networks to approximate functions in 1D.

Study on the complexity of 1D ReLU neural networks, proving growth in linear regions.

Logistic Gaussian process (LGP) priors provide a flexible alternative for modelling unknown densities. The smoothness properties of the density estimates can be controlled through the prior covariance structure of the LGP, but the challenge is the analytically intractable inference. In this paper, we present approximat…

iSTFTNet2 improves iSTFTNet's speed and lightness with 1D-2D CNN.

This paper proposes a novel kernel-based optimization scheme to handle tasks in the analysis, e.g., signal spectral estimation and single-channel source separation of 1D non-stationary oscillatory data. The key insight of our optimization scheme for reconstructing the time-frequency information is that when a nonparame…

Paper proposes a method to reduce hallucinations in diffusion models using Laplacian score sharpening.

Improved robustness of 1D CNNs for heart arrhythmia classification.

Split learning preserves privacy in 1D CNN models for detecting heart abnormalities.

SCORE technique reduces BO's high-dimensional search costs.

A new deep learning benchmark reduces resource needs.

New method trains generative models without discriminators, improving stability and accuracy.

A new density model using Fourier basis achieves better approximations and compression.

Study uses 1D-CNNs to forecast mortality in ELSA survey.

Machine learning is used to approximate density functionals. For the model problem of the kinetic energy of non-interacting fermions in 1d, mean absolute errors below 1 kcal/mol on test densities similar to the training set are reached with fewer than 100 training densities. A predictor identifies if a test density is …

NTS-NOTEARS learns DBNs from time-series data with prior knowledge.

Study shows how 3+1D cosmologies can evolve to de Sitter space under certain conditions.

PAC-Bayes framework fails on simple 1D linear classification task.

Uniqueness of 1D bi-Schrödinger flow proven from flat torus to compact space.

Soil texture is important for many environmental processes. In this paper, we study the classification of soil texture based on hyperspectral data. We develop and implement three 1-dimensional (1D) convolutional neural networks (CNN): the LucasCNN, the LucasResNet which contains an identity block as residual network, a…

Estimates reliability of nuclear fuel using advanced modeling techniques.

Structured CNN designed using the prior information of problems potentially improves efficiency over conventional CNNs in various tasks in solving PDEs and inverse problems in signal processing. This paper introduces BNet2, a simplified Butterfly-Net and inline with the conventional CNN. Moreover, a Fourier transform i…

In this paper, we study the missing sample recovery problem using methods based on sparse approximation. In this regard, we investigate the algorithms used for solving the inverse problem associated with the restoration of missed samples of image signal. This problem is also known as inpainting in the context of image …

Study shows inflation in 3+1D cosmologies with bounded scalar potential and specific symmetry.

Paper extends multi-task Gaussian Cox processes for heterogeneous tasks.

TensorNetwork is an open source library for implementing tensor network algorithms in TensorFlow. We describe a tree tensor network (TTN) algorithm for approximating the ground state of either a periodic quantum spin chain (1D) or a lattice model on a thin torus (2D), and implement the algorithm using TensorNetwork. We…

Estimates latent positions in 1D torus from noisy pairwise affinities.

This study analyzes a non-orientable spacetime model in 1+1D quantum gravity.

Capsule networks excel in understanding spatial relationships in 2D data for vision related tasks. Even though they are not designed to capture 1D temporal relationships, with TimeCaps we demonstrate that given the ability, capsule networks excel in understanding temporal relationships. To this end, we generate capsule…

Topological Quantum Field Theories (TQFTs) pertinent to some emergent low energy phenomena of condensed matter lattice models in 2+1 and 3+1D are explored. Many of our field theories are highly-interacting without free quadratic analogs. Some of our bosonic TQFTs can be regarded as the continuum field theory formulatio…

This paper develops methods for pricing American Parisian options under general Markov models.

Study no-arbitrage conditions in 1D diffusion markets with interest rates.

ABBA creates a new symbolic time series representation based on Brownian bridge.

A simple block configures optimal kernel sizes for time series classification.

The paper proposes an ensemble of convolution-based methods for fault detection in gearboxes.

In this paper, we introduce an inclined curves according to parallel transport frame. Also, we define a vector field called Darboux vector field of an inclined curve in and we give a new characterization such as: "α: I \subset R \rightarrow E^4 is an inclined curve \Leftrightarrow k_1 \int k_1ds + k_2 \int \k_2 +k_3ds …

Paper proposes a faster RAE with sequence-aware encoding.

The author studies regions foliated by 1D families of functions and their applications.

We explore ways in which the covariance ellipsoid ${\cal B}=\{v \in \mathbb{R}^d : \mathbb{E} <X,v>^2 \leq 1\}$ of a centred random vector $X$ in $\mathbb{R}^d$ can be approximated by a simple set. The data one is given for constructing the approximating set consists of $X_1,...,X_N$ that are independent and distribute…

Calibrating a Lévy process usually requires characterizing its jump distribution. Traditionally this problem can be solved with nonparametric estimation using the empirical characteristic functions (ECF), assuming certain regularity, and results to date are mostly in 1D. For multivariate Lévy processes and less smooth …

This paper reconstructs equivalence classes in 1D neural networks.

Ridgeless ReLU networks interpolate datasets and extrapolate based on curvature signs.

Deep neural networks continue to show improved performance with increasing depth, an encouraging trend that implies an explosion in the possible permutations of network architectures and hyperparameters for which there is little intuitive guidance. To address this increasing complexity, we propose Evolutionary DEep Net…

This paper proposes a framework based on deep convolutional neural networks (CNNs) for automatic heart sound classification using short-segments of individual heart beats. We design a 1D-CNN that directly learns features from raw heart-sound signals, and a 2D-CNN that takes inputs of two- dimensional time-frequency fea…

This paper shows the susceptibility of spectrogram-based audio classifiers to adversarial attacks and the transferability of such attacks to audio waveforms. Some commonly used adversarial attacks to images have been applied to Mel-frequency and short-time Fourier transform spectrograms, and such perturbed spectrograms…

Self attention mechanisms have become a key building block in many state-of-the-art language understanding models. In this paper, we show that the self attention operator can be formulated in terms of 1x1 convolution operations. Following this observation, we propose several novel operators: First, we introduce a 2D ve…

The binormal (or vortex filament) equation provides the localized induction approximation of the 3D incompressible Euler equation. We present explicit solutions of the binormal equation in higher-dimensions that collapse in finite time. The local nature of this phenomenon suggests the appearance of singularity in nearb…

A new method for efficient optimal partial transport in 1D.

Energy-efficient sampling for machine learning using magnetic tunnel junctions.