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.
Develops scalable autoencoder for document networks.
To train an inference network jointly with a deep generative topic model, making it both scalable to big corpora and fast in out-of-sample prediction, we develop Weibull hybrid autoencoding inference (WHAI) for deep latent Dirichlet allocation, which infers posterior samples via a hybrid of stochastic-gradient MCMC and…
Develops a flexible deep autoencoding topic model with scalable hybrid Bayesian inference.
We introduce and demonstrate the variational autoencoder (VAE) for probabilistic non-negative matrix factorisation (PAE-NMF). We design a network which can perform non-negative matrix factorisation (NMF) and add in aspects of a VAE to make the coefficients of the latent space probabilistic. By restricting the weights i…
Improved concentration inequalities for sub-Weibull variables enhance statistical and machine learning applications.
A new logit model derived from the Weibull manifold.
AEGCN uses autoencoder constraints to improve graph node classification.
Adversarial training improves graph autoencoder generalization.
AFTNet uses a network-constrained Weibull model for biomarker discovery.
Tiered latent representations and latent spaces for molecular graphs provide a simple but effective way to explicitly represent and utilize groups (e.g., functional groups), which consist of the atom (node) tier, the group tier and the molecule (graph) tier. They can be learned using the tiered graph autoencoder archit…
Weibull weight-scale parameter evolves during AdamW training, with alignment, injection, and decay forces driving its growth and relaxation.
A new model for multiview data analysis using graph autoencoders.
In this paper, we consider survival analysis with right-censored data which is a common situation in predictive maintenance and health field. We propose a model based on the estimation of two-parameter Weibull distribution conditionally to the features. To achieve this result, we describe a neural network architecture …
We propose a symmetric graph convolutional autoencoder which produces a low-dimensional latent representation from a graph. In contrast to the existing graph autoencoders with asymmetric decoder parts, the proposed autoencoder has a newly designed decoder which builds a completely symmetric autoencoder form. For the re…
WTNN models survival with neural networks for maintenance data.
Graphon autoencoder generates graphs with arbitrary sizes using Chebyshev filters.
Efficiently estimates covariance for sub-Weibull vectors with sub-Gaussian rate.
New concentration inequalities for tensors with heavy-tailed coefficients.
Weibull framework diagnoses transformer weight distributions, revealing distinct patterns across modules.
Graph autoencoders (AE) and variational autoencoders (VAE) are powerful node embedding methods, but suffer from scalability issues. In this paper, we introduce FastGAE, a general framework to scale graph AE and VAE to large graphs with millions of nodes and edges. Our strategy, based on an effective stochastic subgraph…
In a previous analysis the problem of "zero-inflated" time data (caused by high frequency trading in the electronic order book) was handled by left-truncating the inter-arrival times. We demonstrated, using rigorous statistical methods, that the Weibull distribution describes the corresponding stochastic dynamics for a…
Possible distributions are discussed for intertrade durations and first-passage processes in financial markets. The view-point of renewal theory is assumed. In order to represent market data with relatively long durations, two types of distributions are used, namely, a distribution derived from the so-called Mittag-Lef…
We present RL-VAE, a graph-to-graph variational autoencoder that uses reinforcement learning to decode molecular graphs from latent embeddings. Methods have been described previously for graph-to-graph autoencoding, but these approaches require sophisticated decoders that increase the complexity of training and evaluat…
Graph regularized autoencoder improves anomaly detection performance.
In this paper, we present a general framework to scale graph autoencoders (AE) and graph variational autoencoders (VAE). This framework leverages graph degeneracy concepts to train models only from a dense subset of nodes instead of using the entire graph. Together with a simple yet effective propagation mechanism, our…
The realized GARCH framework is extended to incorporate the two-sided Weibull distribution, for the purpose of volatility and tail risk forecasting in a financial time series. Further, the realized range, as a competitor for realized variance or daily returns, is employed in the realized GARCH framework. Further, sub-s…
PieClam autoencodes graphs into communities, improving graph anomaly detection.
We analyze waiting times for price changes in a foreign currency exchange rate. Recent empirical studies of high frequency financial data support that trades in financial markets do not follow a Poisson process and the waiting times between trades are not exponentially distributed. Here we show that our data is well ap…
Learning network representations is a fundamental task for many graph applications such as link prediction, node classification, graph clustering, and graph visualization. Many real-world networks are interpreted as dynamic networks and evolve over time. Most existing graph embedding algorithms were developed for stati…
DefenseVGAE defends graph neural networks against adversarial attacks.
Graph autoencoders (AE) and variational autoencoders (VAE) recently emerged as powerful node embedding methods. In particular, graph AE and VAE were successfully leveraged to tackle the challenging link prediction problem, aiming at figuring out whether some pairs of nodes from a graph are connected by unobserved edges…
Improved community detection and link prediction with GAE and VGAE.
EVGAE improves VGAE's latent representation learning by mitigating over-pruning.
Graph embedding is an effective method to represent graph data in a low dimensional space for graph analytics. Most existing embedding algorithms typically focus on preserving the topological structure or minimizing the reconstruction errors of graph data, but they have mostly ignored the data distribution of the laten…
We examine two fundamental tasks associated with graph representation learning: link prediction and semi-supervised node classification. We present a novel autoencoder architecture capable of learning a joint representation of both local graph structure and available node features for the multi-task learning of link pr…
A deep learning model organizes RNA graphs to reveal folding patterns and properties.
Graph autoencoders (AE) and variational autoencoders (VAE) recently emerged as powerful node embedding methods, with promising performances on challenging tasks such as link prediction and node clustering. Graph AE, VAE and most of their extensions rely on graph convolutional networks (GCN) to learn vector space repres…
GAEs are shown to be implicitly contrastive learners, revealing new design axes.
Paper proposes MMW distribution for better financial risk modeling.
DECAF-GAD improves fairness in autoencoder-based GAD models without sacrificing performance.
Estimates change points in Weibull time series with copulas.
VACA models graph data for causal inference without hidden confounders.
Over the last few years, graph autoencoders (AE) and variational autoencoders (VAE) emerged as powerful node embedding methods, with promising performances on challenging tasks such as link prediction and node clustering. Graph AE, VAE and most of their extensions rely on multi-layer graph convolutional networks (GCN) …
Proposes autoencoding with random forests using spectral graph theory.
Study on hidden units in finite Bayesian neural networks and their tail properties.
A novel disentangled graph autoencoder improves treatment effect estimation from networked observational data.
Unified framework for constructing nonconvex sparse recovery methods.
We improve a graph generation model to accurately recover Barabási-Albert graph parameters.