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.
Proposes a new convolutional neural network for non-grid data.
This research studies affine invariance in continuous-domain convolutional neural networks.
Proposes continuous convolution layers for flexible feature map resizing.
CGNNs use wavelets for continuous function generation in infinite-dimensional spaces.
Lie groupoid equivariant neural networks are a new type of neural network.
Improved robustness of 1D CNNs for heart arrhythmia classification.
GCNs converge and remain stable on large random graphs, revealing geometric insights.
Numerous important problems can be framed as learning from graph data. We propose a framework for learning convolutional neural networks for arbitrary graphs. These graphs may be undirected, directed, and with both discrete and continuous node and edge attributes. Analogous to image-based convolutional networks that op…
First steps towards a mathematical theory of deep convolutional neural networks for feature extraction were made---for the continuous-time case---in Mallat, 2012, and Wiatowski and Bölcskei, 2015. This paper considers the discrete case, introduces new convolutional neural network architectures, and proposes a mathemati…
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, …
Paper tackles missing data in irregularly-sampled time series.
Deep learning has been widely applied and brought breakthroughs in speech recognition, computer vision, and many other domains. The involved deep neural network architectures and computational issues have been well studied in machine learning. But there lacks a theoretical foundation for understanding the approximation…
The understanding of geographical reality is a process of data representation and pattern discovery. Former studies mainly adopted continuous-field models to represent spatial variables and to investigate the underlying spatial continuity/heterogeneity in the regular spatial domain. In this article, we introduce a more…
The translation equivariance of convolutional layers enables convolutional neural networks to generalize well on image problems. While translation equivariance provides a powerful inductive bias for images, we often additionally desire equivariance to other transformations, such as rotations, especially for non-image d…
Deep learning has the potential to revolutionize quantum chemistry as it is ideally suited to learn representations for structured data and speed up the exploration of chemical space. While convolutional neural networks have proven to be the first choice for images, audio and video data, the atoms in molecules are not …
NAS helps find best neural network designs.
A new FFT method for Heston model option pricing with explicit error bounds.
Over 50 million scholarly articles have been published: they constitute a unique repository of knowledge. In particular, one may infer from them relations between scientific concepts, such as synonyms and hyponyms. Artificial neural networks have been recently explored for relation extraction. In this work, we continue…
Study on VC dimension of GCNNs with input resolution effects.
Motivated by the study of Hörmander's sums-of-squares operators and their generalizations, we define the convolution algebra of transverse distributions associated to a singular foliation. We prove that this algebra is represented as continuous linear operators on the spaces of smooth functions and generalized function…
The splendid success of convolutional neural networks (CNNs) in computer vision is largely attributable to the availability of massive annotated datasets, such as ImageNet and Places. However, in medical imaging, it is challenging to create such large annotated datasets, as annotating medical images is not only tedious…
We introduce two constructions in geometric deep learning for 1) transporting orientation-dependent convolutional filters over a manifold in a continuous way and thereby defining a convolution operator that naturally incorporates the rotational effect of holonomy; and 2) allowing efficient evaluation of manifold convol…
The classical Serre-Swan's theorem defines a bijective correspondence between vector bundles and finitely generated projective modules over the algebra of continuous functions on some compact Hausdorff topological space. We extend these results to obtain a correspondence between the category of representations of an et…
We propose a novel continual learning method called Residual Continual Learning (ResCL). Our method can prevent the catastrophic forgetting phenomenon in sequential learning of multiple tasks, without any source task information except the original network. ResCL reparameterizes network parameters by linearly combining…
ShuffleNet is a state-of-the-art light weight convolutional neural network architecture. Its basic operations include group, channel-wise convolution and channel shuffling. However, channel shuffling is manually designed empirically. Mathematically, shuffling is a multiplication by a permutation matrix. In this paper, …
There has been a recent shift in sequence-to-sequence modeling from recurrent network architectures to convolutional network architectures due to computational advantages in training and operation while still achieving competitive performance. For systems having limited long-term temporal dependencies, the approximatio…
Deep convolutional neural networks have led to breakthrough results in numerous practical machine learning tasks such as classification of images in the ImageNet data set, control-policy-learning to play Atari games or the board game Go, and image captioning. Many of these applications first perform feature extraction …
New framework prevents forgetting in sequential learning tasks.
This study presents a novel end-to-end architecture that learns hierarchical representations from raw EEG data using fully convolutional deep neural networks for the task of neonatal seizure detection. The deep neural network acts as both feature extractor and classifier, allowing for end-to-end optimization of the sei…
Study risk sharing with Lambda VaR under diverse beliefs.
Quantum CNNs improve on multi-channel data processing.
Optimal task order improves continual learning performance.
A scattering transform defines a signal representation which is invariant to translations and Lipschitz continuous relatively to deformations. It is implemented with a non-linear convolution network that iterates over wavelet and modulus operators. Lipschitz continuity locally linearizes deformations. Complex classes o…
Given a finitely generated and projective Lie-Rinehart algebra, we show that there is a continuous homomorphism of complete commutative Hopf algebroids between the completion of the finite dual of its universal enveloping Hopf algebroid and the associated convolution algebra. The topological Hopf algebroid structure of…
Graph convolutions can enhance high frequencies, leading to over-sharpening.
Machine Learning on graph-structured data is an important and omnipresent task for a vast variety of applications including anomaly detection and dynamic network analysis. In this paper, a deep generative model is introduced to capture continuous probability densities corresponding to the nodes of an arbitrary graph. I…
DNArch learns CNN architectures by backpropagation.
Rotation intertwining maps from the set of convex bodies in Rn into itself that are continuous linear operators with respect to Minkowski and Blaschke addition are investigated. The main focus is on Blaschke-Minkowski homomorphisms. We show that such maps are represented by a spherical convolution operator. An applicat…
With a view towards applications in the theory of infinite-dimensional representations of finite-dimensional Lie supergroups, we introduce a new category of supermanifolds. In this category, supermanifolds of `maps' and `fields' (fibre bundle sections) exist. In particular, loop supergroups can be realised globally in …
Exact bounds derived for neural network outputs with noisy inputs.
Novel Haar-Laplacian for directed graphs enhances spectral graph applications.
ConEx learns complex embeddings for knowledge graphs, improving link prediction.
DeepPocket uses graph convolutional reinforcement learning for better financial portfolio management.
Framework detects and ranks suspicious market manipulation using temporal convolutions and expert assessment.
INDEQS: A Graph-Based Neural Controlled Differential Equation Framework for Forecasting
New methods improve translation-equivariant neural processes for modeling unknown functions.
This paper uses deep RL to optimize market quotes from LOB data.
Monotone aggregation of dependent random vectors has an absolutely continuous distribution under certain conditions.