arXiv research

A simple strategy prevents negative transfer in transfer learning.

PRISMA uses PDE residuals for fast, robust, and accurate inference.

The Wodzicki residue and the cut-off integral extend to classical symbol-valued forms. We show that they obey a Stokes' type property and that the extended Wodzicki residue can be interpreted as a complex residue like the ordinary one. In the case of cut-off integrals, Stokes' property (i.e. vanishing on exact forms) o…

Mathematical formulas for elliptic curve integrals solve anomaly equations.

The canonical trace and the Wodzicki residue on classical pseudodifferential operators on a closed manifold are characterised by their locality and shown to be preserved under lifting to the universal covering as a result of their local feature. As a consequence, we lift a class of spectral $ζ$-invariants using lifted …

RFRBoost uses random features to boost deep residual neural networks, improving performance and computational efficiency.

Deviance-style normalization for sparse, jointly overdispersed count matrices

RDL-Net improves speech enhancement with fewer parameters and better performance.

This research improves asset life prediction by integrating deep learning with mixture distributions.

3D BF theory on certain 3-manifolds evaluated via residues and large k limits.

SRFRN accelerates image super-resolution using shallow residual units.

Fast nonparametric conditional independence testing via two-stage regression

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 …

We present a continuous formulation of machine learning, as a problem in the calculus of variations and differential-integral equations, in the spirit of classical numerical analysis. We demonstrate that conventional machine learning models and algorithms, such as the random feature model, the two-layer neural network …

Extends Hawkes process for flexible residual modeling in point processes.

SX-GeoTree improves spatially coherent explanations in geospatial regression trees.

We provide analytical tools for pricing power options with exotic features (capped or log payoffs, gap options ...) in the framework of exponential Lévy models driven by one-sided stable or tempered stable processes. Pricing formulas take the form of fast converging series of powers of the log-forward moneyness and of …

We show that Residual Networks (ResNet) is equivalent to boosting feature representation, without any modification to the underlying ResNet training algorithm. A regret bound based on Online Gradient Boosting theory is proved and suggests that ResNet could achieve Online Gradient Boosting regret bounds through neural n…

Paper uses VAEs to control IVS features for financial modeling.

Study the intersection of positive closed currents using tangent currents and King's residue formula.

Paper improves bike-sharing demand prediction by adapting to changing patterns.

Method uses random forest with distance covariance for transfer learning in healthcare.

In this paper, we aim to understand Residual Network (ResNet) in a scientifically sound way by providing a bridge between ResNet and Feynman path integral. In particular, we prove that the effect of residual block is equivalent to partial differential equation, and the ResNet transforming process can be equivalently co…

Graph neural networks suffer from oversmoothing, but adding residual connections helps.

The paper studies residues of manifolds and their applications in geometry.

Inverse modeling for the estimation of non-Gaussian hydraulic conductivity fields in subsurface flow and solute transport models remains a challenging problem. This is mainly due to the non-Gaussian property, the non-linear physics, and the fact that many repeated evaluations of the forward model are often required. In…

Given a compatible vector field on a compact connected almost-complex manifold, we show in this article that the multiplicities of eigenvalues among the zero point set of this vector field have intimate relations. We highlight a special case of our result and reinterpret it as a vanishing-type result in the framework o…

Image super-resolution is a challenging task and has attracted increasing attention in research and industrial communities. In this paper, we propose a novel end-to-end Attention-based DenseNet with Residual Deconvolution named as ADRD. In our ADRD, a weighted dense block, in which the current layer receives weighted f…

This paper proposes a Residual Convolutional Neural Network (ResNet) based on speech features and trained under Focal Loss to recognize emotion in speech. Speech features such as Spectrogram and Mel-frequency Cepstral Coefficients (MFCCs) have shown the ability to characterize emotion better than just plain text. Furth…

A beta function for double layers is defined and analyzed.

Enhanced image denoising with MWRDCNN using residual dense blocks.

Deep learning enhances options hedging performance.

New bounds on ReLU networks for low-regular functions.

Consider the space $R_Δ$ of rational functions of several variables with poles on a fixed arrangement $Δ$ of hyperplanes. We obtain a decomposition of $R_Δ$ as a module over the ring of differential operators with constant coefficients. We generalize to the space $R_Δ$ the notions of principal part and of residue, and …

New integral theorems improve density function estimations.

We present in this paper a model for forecasting short-term power loads based on deep residual networks. The proposed model is able to integrate domain knowledge and researchers' understanding of the task by virtue of different neural network building blocks. Specifically, a modified deep residual network is formulated…

We improve optimization for data with varying variance.

CIRCE measures conditional independence for learning invariant features.

Improved ResNets and DenseNets models for better feature reuse.

This work proposes a novel autoencoder for fusing visible and infrared images.

RKD improves model compression by distilling residual knowledge from a deep teacher model.

We prove an explicit residue formula for a meromorphic continuation of conformally covariant integral operators between differential forms on ${\bf R}^n$ and on its hyperplane. The results provide a simple and new construction of the conformally covariant differential symmetry breaking operators between differential fo…

Residual networks with depthwise hyperparameter scaling transfer optimal hyperparameters across width and depth.

This paper has four main parts. In the first part, we construct a noncommutative residue for the hypoelliptic calculus on Heisenberg manifolds, that is, for the class of Heisenberg PsiDOs introduced by Beals-Greiner and Taylor. This noncommutative residue appears as the residual trace on integer order Heisenberg PsiDOs…

Two methods improve Gaussian process predictive distributions' calibration.

Model predicts option movements using residual transactions for better market timing.

In general, image restoration involves mapping from low quality images to their high-quality counterparts. Such optimal mapping is usually non-linear and learnable by machine learning. Recently, deep convolutional neural networks have proven promising for such learning processing. It is desirable for an image processin…

SCORE improves tree-based predictions with boosted residual extraTrees.