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.
Two novel methods improve network embedding for completely-imbalanced labels.
AI helps complete ancient tablets with missing parts.
A matrix network is a family of matrices, with relatedness modeled by a weighted graph. We consider the task of completing a partially observed matrix network. We assume a novel sampling scheme where a fraction of matrices might be completely unobserved. How can we recover the entire matrix network from incomplete obse…
Tackles network structure inference from time series data using GNN.
Paper proposes a forecasting solution for network-rollout planning.
A new tensor completion method using tensor networks with Tucker wrapper.
Sparse codes improve optimal control tasks with correlated inputs.
Improved hardness results for clearing payments in financial networks with CDSs.
Matrix completion is one of the key problems in signal processing and machine learning, with applications ranging from image pro- cessing and data gathering to classification and recommender sys- tems. Recently, deep neural networks have been proposed as la- tent factor models for matrix completion and have achieved st…
Several algorithms have been proposed to filter information on a complete graph of correlations across stocks to build a stock-correlation network. Among them the planar maximally filtered graph (PMFG) algorithm uses edges to build a graph whose features include a high frequency of small cliques and a good clust…
Locally learned synaptic failure enables complete Bayesian inference.
Alternatives to recurrent neural networks, in particular, architectures based on attention or convolutions, have been gaining momentum for processing input sequences. In spite of their relevance, the computational properties of these alternatives have not yet been fully explored. We study the computational power of two…
Dropout controls model capacity in deep learning and matrix completion.
Unified framework for complex financial networks using lattice theory.
New deep learning model for matrix completion combining linear and nonlinear relationships.
Matrix completion models are among the most common formulations of recommender systems. Recent works have showed a boost of performance of these techniques when introducing the pairwise relationships between users/items in the form of graphs, and imposing smoothness priors on these graphs. However, such techniques do n…
Researchers prove Transformers are Turing-complete and analyze their components.
Improves generative model coverage of underrepresented modes.
Combining explicit and implicit regularization improves deep learning performance without needing depth.
Human explanations of high-level decisions are often expressed in terms of key concepts the decisions are based on. In this paper, we study such concept-based explainability for Deep Neural Networks (DNNs). First, we define the notion of completeness, which quantifies how sufficient a particular set of concepts is in e…
LMConv improves autoregressive models for image generation and completion.
The ubiquitous proliferation of online social networks has led to the widescale emergence of relational graphs expressing unique patterns in link formation and descriptive user node features. Matrix Factorization and Completion have become popular methods for Link Prediction due to the low rank nature of mutual node fr…
Deep neural networks solve stochastic control problems with delay.
Predicting the completion time of business process instances would be a very helpful aid when managing processes under service level agreement constraints. The ability to know in advance the trend of running process instances would allow business managers to react in time, in order to prevent delays or undesirable situ…
New matrix completion method for arbitrary sampling patterns using network flows.
Proposes SE(3) equivariant graph neural networks with local frames for efficient geometric approximation.
How can we recognise social roles of people, given a completely unlabelled social network? We present a transfer learning approach to network role classification based on feature transformations from each network's local feature distribution to a global feature space. Experiments are carried out on real-world datasets.…
Efficiently verifies neural networks by handling neuron splits, improving speed and accuracy.
Since the 2007-2009 financial crisis, substantial academic effort has been dedicated to improving our understanding of interbank lending networks (ILNs). Because of data limitations or by choice, the literature largely lacks multiple loan maturities. We employ a complete interbank loan contract dataset to investigate w…
WGNN learns graph representations from incomplete attribute data.
We propose an inductive matrix completion model without using side information. By factorizing the (rating) matrix into the product of low-dimensional latent embeddings of rows (users) and columns (items), a majority of existing matrix completion methods are transductive, since the learned embeddings cannot generalize …
New model for network analysis using functional data.
Proposes a new model for image restoration combining deep learning and total variation.
Quantum neural networks need both data-dependent and trainable unitaries for effective geometric deformation.
Autoencoders are popular among neural-network-based matrix completion models due to their ability to retrieve potential latent factors from the partially observed matrices. Nevertheless, when training data is scarce their performance is significantly degraded due to overfitting. In this paper, we mit- igate overfitting…
Music SketchNet generates missing measures in incomplete music pieces, guided by user input.
A neural network method for financial data nowcasting.
Generative adversarial networks (GANs) have been shown to provide an effective way to model complex distributions and have obtained impressive results on various challenging tasks. However, typical GANs require fully-observed data during training. In this paper, we present a GAN-based framework for learning from comple…
Jiří Matoušek (1963-2015) had many breakthrough contributions in mathematics and algorithm design. His milestone results are not only profound but also elegant. By going beyond the original objects --- such as Euclidean spaces or linear programs --- Jirka found the essence of the challenging mathematical/algorithmic pr…
This paper considers the computational power of constant size, dynamic Bayesian networks. Although discrete dynamic Bayesian networks are no more powerful than hidden Markov models, dynamic Bayesian networks with continuous random variables and discrete children of continuous parents are capable of performing Turing-co…
We prove that there are no networks homeomorphic to the Greek "theta" letter (a double cell) embedded in the plane with two triple junctions with angles of degrees, such that under the motion by curvature they are self-similarly shrinking. This fact completes the classification of the self-similarly shrinking net…
The paper analyzes implicit regularization in tensor factorization using neural networks.
New CRM models for sparse networks with linear edge growth.
Deep Matrix Factorization (DMF) is an emerging approach to the problem of matrix completion. Recent works have established that gradient descent applied to a DMF model induces an implicit regularization on the rank of the recovered matrix. In this work we interpret the DMF model through the lens of spectral geometry. T…
Graph Neural Networks (GNN) are a promising technique for bridging differential programming and combinatorial domains. GNNs employ trainable modules which can be assembled in different configurations that reflect the relational structure of each problem instance. In this paper, we show that GNNs can learn to solve, wit…
We study a problem of geometric graph theory: We determine the triply periodic graph in Euclidean 3-space which minimizes length among all graphs spanning a fundamental domain of 3-space with the same volume. The minimizer is the so-called srs network with quotient the complete graph on four vertices . The network…
Adaptive algorithm learns tensor network structures from data.
GCN adapted for graphs with missing features, improving performance.