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.
This paper introduces a new method for neural networks that doesn't need a global coordinate system.
We propose PLLay, a novel topological layer for general deep learning models based on persistence landscapes, in which we can efficiently exploit the underlying topological features of the input data structure. In this work, we show differentiability with respect to layer inputs, for a general persistent homology with …
Topology applied to real world data using persistent homology has started to find applications within machine learning, including deep learning. We present a differentiable topology layer that computes persistent homology based on level set filtrations and edge-based filtrations. We present three novel applications: th…
Given a complete non-compact surface embedded in R^3, we consider the Dirichlet Laplacian in a layer of constant width about the surface. Using an intrinsic approach to the layer geometry, we generalise the spectral results of an original paper by Duclos et al. to the situation when the surface does not possess poles. …
Neural networks simplify complex data topologies into simpler ones.
Paper learns DAGs with quadratic variance functions efficiently.
Single wide layer followed by a pyramidal structure ensures global convergence in deep networks.
NeuroFabric proposes a method to optimize sparse network training topologies.
We simplify neural networks to 3D to study their topological changes.
The paper sets limits on neural network sizes based on dataset shapes.
Smectic liquid crystals are materials formed by stacking deformable, fluid layers. Though smectics prefer to have flat, uniformly-spaced layers, boundary conditions can impose curvature on the layers. Since the layer spacing and curvature are intertwined, the problem of finding minimal configurations for the layers bec…
Efficiently learns linear non-Gaussian DAGs with noisy nodes.
In established network architectures, shortcut connections are often used to take the outputs of earlier layers as additional inputs to later layers. Despite the extraordinary effectiveness of shortcuts, there remain open questions on the mechanism and characteristics. For example, why are shortcuts powerful? Why do sh…
Lie groupoid equivariant neural networks are a new type of neural network.
Network analysis reveals distinct financial relationships among Euro Area banks.
The interbank market has a natural multiplex network representation. We employ a unique database of supervisory reports of Italian banks to the Banca d'Italia that includes all bilateral exposures broken down by maturity and by the secured and unsecured nature of the contract. We find that layers have different topolog…
Combines gradient-based and competitive learning for unsupervised feature extraction.
Proposes deep graph persistence to address neural persistence issues in deep learning.
In this paper we propose a generalization of deep neural networks called deep function machines (DFMs). DFMs act on vector spaces of arbitrary (possibly infinite) dimension and we show that a family of DFMs are invariant to the dimension of input data; that is, the parameterization of the model does not directly hinge …
Dropout and similar stochastic neural network regularization methods are often interpreted as implicitly averaging over a large ensemble of models. We propose STE (stochastically trained ensemble) layers, which enhance the averaging properties of such methods by training an ensemble of weight matrices with stochastic r…
Predictive Sparse Manifold Transform learns dynamic video sequences.
An asset network systemic risk (ANWSER) model is presented to investigate the impact of how shadow banks are intermingled in a financial system on the severity of financial contagion. Particularly, the focus of this study is the impact of the following three representative topologies of an interbank loan network betwee…
TOGL adds topological info to GNNs, improving graph and node classification.
Improved bounds on neural network regions using activation histograms.
Deep Learning methods, specifically convolutional neural networks (CNNs), have seen a lot of success in the domain of image-based data, where the data offers a clearly structured topology in the regular lattice of pixels. This 4-neighbourhood topological simplicity makes the application of convolutional masks straightf…
Efficient memory layer improves graph neural networks for graph classification and regression.
Constructs dg categories from surfaces using Khovanov homology.
The theoretical explanation for deep neural network (DNN) is still an open problem. In this paper DNN is considered as a discrete-time dynamical system due to its layered structure. The complexity provided by the nonlinearity in the dynamics is analyzed in terms of topological entropy and chaos characterized by Lyapuno…
This paper presents a new artificial neuron model capable of learning its receptive field in the topological domain of inputs. The model provides adaptive and differentiable local connectivity (plasticity) applicable to any domain. It requires no other tool than the backpropagation algorithm to learn its parameters whi…
Empirical investor networks (EIN) proposed by \cite{Ozsoylev-Walden-Yavuz-Bildik-2014-RFS} are assumed to capture the information spreading path among investors. Here, we perform a comparative analysis between the EIN and the cellphone communication networks (CN) to test whether EIN is an information exchanging network…
The paper examines how neural network topology affects adversarial robustness.
Poor approximators found in neural networks and random feature models.
Entropy data replaces classical charts for smooth manifolds.
We introduce a new function-preserving transformation for efficient neural architecture search. This network transformation allows reusing previously trained networks and existing successful architectures that improves sample efficiency. We aim to address the limitation of current network transformation operations that…
This work bridges competitive learning with gradient-based learning for faster feature extraction.
Paper estimates neural network size needed for topology learning.
Deep learning enhances Hamiltonian Monte Carlo for sampling gauge field configurations.
Fog learning distributes ML model training across heterogeneous devices and networks.
Multiplex networks, a special type of multilayer networks, are increasingly applied in many domains ranging from social media analytics to biology. A common task in these applications concerns the detection of community structures. Many existing algorithms for community detection in multiplexes attempt to detect commun…
This paper improves deep forest models with soft routing and topology learning.
New method integrates topological knowledge into data embeddings.
Global convergence proved for three-layer neural networks in mean field regime.
The paper proves skip connections help neural networks avoid shallow local minima.
L-CNNs learn gauge invariant quantities on lattices.
The worldwide trade network has been widely studied through different data sets and network representations with a view to better understanding interactions among countries and products. Here we investigate international trade through the lenses of the single-layer, multiplex, and multi-layer networks. We discuss diffe…
We build polyhedral complexes in Rn that coincide with dyadic grids with different orientations, while keeping uniform lower bounds (depending only on n) on the flatness of the added polyhedrons including their subfaces in all dimensions. After the definitions and first properties of compact Euclidean polyhedrons and c…
We propose Sparse Neural Network architectures that are based on random or structured bipartite graph topologies. Sparse architectures provide compression of the models learned and speed-ups of computations, they can also surpass their unstructured or fully connected counterparts. As we show, even more compact topologi…
Z-GCNETs uses topological data to improve time series forecasting.