arXiv research

Study approximates weak error for specific stochastic models with rough and Gaussian mean-reverting volatility.

Most methods for time series classification that attain state-of-the-art accuracy have high computational complexity, requiring significant training time even for smaller datasets, and are intractable for larger datasets. Additionally, many existing methods focus on a single type of feature such as shape or frequency. …

The study quantifies how many objects can be linearly classified under all views.

This study compares RNN and CNN for predicting wave propagation using the Saint-Venant equations.

ThriftyNet uses a single convolutional layer recursively to maximize parameter usage.

This paper provides an initial investigation on the application of convolutional neural networks (CNNs) for fingerprint-based positioning using measured massive MIMO channels. When represented in appropriate domains, massive MIMO channels have a sparse structure which can be efficiently learned by CNNs for positioning …

Paper analyzes and improves graph convolutional networks for node classification.

The paper defines and analyzes set-valued stochastic integrals for Lévy processes.

Paper proposes a new LSTM model for spatio-temporal learning.

Deep neural networks estimate long memory parameters efficiently.

Improved model for non-smooth signals with complex spectra.

New method transforms complex stochastic equations into simpler ones for efficient simulation.

Convolutional Bayesian filtering generalizes state estimation by incorporating inequality conditions.

This paper describes a novel approach of packing sparse convolutional neural networks for their efficient systolic array implementations. By combining subsets of columns in the original filter matrix associated with a convolutional layer, we increase the utilization efficiency of the systolic array substantially (e.g.,…

Convolution is a central operation in Convolutional Neural Networks (CNNs), which applies a kernel to overlapping regions shifted across the image. However, because of the strong correlations in real-world image data, convolutional kernels are in effect re-learning redundant data. In this work, we show that this redund…

Phase segregation, the process by which the components of a binary mixture spontaneously separate, is a key process in the evolution and design of many chemical, mechanical, and biological systems. In this work, we present a data-driven approach for the learning, modeling, and prediction of phase segregation. A direct …

SigMA uses signatures and attention to estimate parameters in fBm-driven SDEs.

DFS dynamically decides bitwidths for layers to balance accuracy and efficiency.

Automated protein structure prediction from cryo-EM data.

MultiRocket boosts TSC speed and accuracy with pooling and transformations.

In this work we present a new approach on studying dynamical systems. Combining the two ways of expressing the uncertainty, using probabilistic theory and credibility theory, we have research the generalized fractional hybrid equations. We have introduced the concepts of generalized fractional Wiener process, generaliz…

GNNs improve semi-supervised node regression, but why? We explain.

Deep learning improves plaque prediction for coronary artery health.

Methods from the geometry of nonholonomic manifolds and Lagrange-Finsler spaces are applied in fractional calculus with Caputo derivatives and for elaborating models of fractional gravity and fractional Lagrange mechanics. The geometric data for such models are encoded into (fractional) bi-Hamiltonian structures and as…

New algorithms achieve optimal robustness in stochastic convex optimization under contamination.

We propose an incremental training method that partitions the original network into sub-networks, which are then gradually incorporated in the running network during the training process. To allow for a smooth dynamic growth of the network, we introduce a look-ahead initialization that outperforms the random initializa…

Introduces fractional k-dimensional measure bridging fractional length and area.

The theory of derivative of noninteger order goes back to Leibniz, Liouville and Riemann. Derivatives of fractional order have found many applications in recent studies in mechanics, physics, economics. In this paper we define the fractional tangent bundle on a manifold, using a method of Radu Miron. The fractional Lei…

Image reconstruction in low-count PET is particularly challenging because gammas from natural radioactivity in Lu-based crystals cause high random fractions that lower the measurement signal-to-noise-ratio (SNR). In model-based image reconstruction (MBIR), using more iterations of an unregularized method may increase t…

Let $S_g$ be a closed orientable surface of genus $g \geq 2$ and $C$ a simple closed nonseparating curve in $F$. Let $t_C$ denote a left handed Dehn twist about $C$. A \textit{fractional power} of $t_C$ of \textit{exponent} $\fraction{\ell}{n}$ is an $h \in \Mod(S_g)$ such that $h^n = t_C^{\ell}$. Unlike a root of a $t…

We formulate the fractional Ricci flow theory for (pseudo) Riemannian geometries enabled with nonholonomic distributions defining fractional integro-differential structures, for non-integer dimensions. There are constructed fractional analogs of Perelman's functionals and derived the corresponding fractional evolution …

Using Caputo fractional derivative of order $α$ we build the fractional jet bundle of order $α$ and its main geometrical structures. Defined on that bundle, some fractional dynamical systems with applications to economics are studied.

Volatility roughness studied using fractional noise-driven models.

Using the reviewed Riemann-Liouville fractional derivative we introduce the fractional osculator Lagrange space of k order and the main structures on it. The results are applied at the k order fractional prolongation of Lagrange, Finsler and Riemann fractional structures.

We propose a new model for unsupervised document embedding. Leading existing approaches either require complex inference or use recurrent neural networks (RNN) that are difficult to parallelize. We take a different route and develop a convolutional neural network (CNN) embedding model. Our CNN architecture is fully par…

MINIROCKET speeds up time series classification by 75x.

Develops fractional de Rham theory for Maxwell equations.

Modeling financial markets with memory using fractional calculus and Brownian motion.

Long and short memory in economic processes is usually described by the so-called discrete fractional differencing and fractional integration. We prove that the discrete fractional differencing and integration are the Grunwald-Letnikov fractional differences of non-integer order d. Equations of ARIMA(p,d,q) and ARFIMA(…

In this paper we established the condition for a curve to satisfy stochas- tic fractional HP (Hamilton-Pontryagin) equations. These equations are described using It^o integral. We have also considered the case of stochastic fractional Hamiltonian equa- tions, for a hyperregular Lagrange function. From the stochastic fr…

We study the fractional gravity for spacetimes with non-integer dimensions. Our constructions are based on a geometric formalism with the fractional Caputo derivative and integral calculus adapted to nonolonomic distributions. This allows us to define a fractional spacetime geometry with fundamental geometric/physical …

Extends fractional $L^p$ uncertainty principles with extremizers and stability results.

Approximates derivative pricing under fractional stochastic volatility.

New method uses fractional posteriors for semiparametric inference with improved uncertainty quantification.

Graph convolution networks (GCN) have emerged as the leading method to classify node classes in networks, and have reached the highest accuracy in multiple node classification tasks. In the absence of available tagged samples, active learning methods have been developed to obtain the highest accuracy using the minimal …

New measure predicts deep neural network generalization better than existing ones.

In this paper we introduce a link between geometry of ordinary continued fractions and trajectories of points that moves according to the second Kepler law. We expand geometric interpretation of ordinary continued fractions to the case of continued fractions with arbitrary elements.

The paper studies inequalities for fractional GJMS operators on conformal infinity.