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.
GER learns particle dynamics from unpaired snapshots using physics-informed GANs.
This paper improves deep learning model consistency through ensemble methods.
New method improves ensemble quality by exploring the pre-train basin more effectively.
This work improves distribution recovery from sparse data using Random Forest implicit regularization.
Temporal networks are ubiquitous and evolve over time by the addition, deletion, and changing of links, nodes, and attributes. Although many relational datasets contain temporal information, the majority of existing techniques in relational learning focus on static snapshots and ignore the temporal dynamics. We propose…
CT-OT Flow estimates continuous-time dynamics from discrete snapshots.
Physics-informed methods infer spatial dynamics from static snapshots, but limits exist.
Deep learning architectures have proved versatile in a number of drug discovery applications, including the modelling of in vitro compound activity. While controlling for prediction confidence is essential to increase the trust, interpretability and usefulness of virtual screening models in drug discovery, techniques t…
Ensembles of deep neural networks significantly improve generalization accuracy. However, training neural network ensembles requires a large amount of computational resources and time. State-of-the-art approaches either train all networks from scratch leading to prohibitive training cost that allows only very small ens…
DDD reformulated for sparse matrices, integrating trajectory and snapshot time series data.
Offline Signature Verification (OSV) is a challenging pattern recognition task, especially in presence of skilled forgeries that are not available during training. This study aims to tackle its challenges and meet the substantial need for generalization for OSV by examining different loss functions for Convolutional Ne…
The loss functions of deep neural networks are complex and their geometric properties are not well understood. We show that the optima of these complex loss functions are in fact connected by simple curves over which training and test accuracy are nearly constant. We introduce a training procedure to discover these hig…
TNDE quantifies dynamic gene drivers from single-cell snapshots.
We study the inference of a model of dynamic networks in which both communities and links keep memory of previous network states. By considering maximum likelihood inference from single snapshot observations of the network, we show that link persistence makes the inference of communities harder, decreasing the detectab…
Uncertainty quantification for deep learning is a challenging open problem. Bayesian statistics offer a mathematically grounded framework to reason about uncertainties; however, approximate posteriors for modern neural networks still require prohibitive computational costs. We propose a family of algorithms which split…
Hybrid engine analyzes news sentiment for markets in real-time.
Complex high dimensional stochastic dynamic systems arise in many applications in the natural sciences and especially biology. However, while these systems are difficult to describe analytically, "snapshot" measurements that sample the output of the system are often available. In order to model the dynamics of such sys…
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…
New method infers population dynamics from snapshots using path space optimization.
SnapMMD forecasts cell differentiation outcomes from snapshot data.
New method learns population dynamics from snapshots using JKO scheme and inverse optimization.
In a dynamic network, the neighborhood of the vertices evolve across different temporal snapshots of the network. Accurate modeling of this temporal evolution can help solve complex tasks involving real-life social and interaction networks. However, existing models for learning latent representation are inadequate for …
Efficient neural network ensembles improve image classification reliability and uncertainty quantification.
Unified framework for discrete diffusion modeling with flexible noising processes.
New method learns cell trajectories from multiple snapshots.
New method learns population dynamics from snapshots, outperforming existing models.
A neural network, IHT-Net, improves DOA estimation with sparse arrays.
3MSBM learns smooth trajectories from multiple snapshots.
LAD detects anomalies in dynamic graphs using Laplacian matrix.
Paper improves DOA estimation in sparse arrays using Siamese neural networks.
Numerous networks in the real world change over time, in the sense that nodes and edges enter and leave the networks. Various dynamic random graph models have been proposed to explain the macroscopic properties of these systems and to provide a foundation for statistical inferences and predictions. It is of interest to…
Networks evolve continuously over time with the addition, deletion, and changing of links and nodes. Such temporal networks (or edge streams) consist of a sequence of timestamped edges and are seemingly ubiquitous. Despite the importance of accurately modeling the temporal information, most embedding methods ignore it …
DiffVolume generates realistic volume snapshots for LOBs.
The paper explores dynamic ensembles for multi-step forecasting.
MSBM extends SB for multi-marginal trajectory inference.
In this work, we consider the problem of combining link, content and temporal analysis for community detection and prediction in evolving networks. Such temporal and content-rich networks occur in many real-life settings, such as bibliographic networks and question answering forums. Most of the work in the literature (…
Ensembles dynamic models using random feature approximations.
Due to the dynamic nature of biological systems, biological networks underlying temporal process such as the development of {\it Drosophila melanogaster} can exhibit significant topological changes to facilitate dynamic regulatory functions. Thus it is essential to develop methodologies that capture the temporal evolut…
This paper proves long-time accuracy of ensemble Kalman filters for chaotic and machine-learned systems.
This paper studies recursive ensembles driven by Fibonacci updates, improving learning dynamics.
We propose a non-parametric link prediction algorithm for a sequence of graph snapshots over time. The model predicts links based on the features of its endpoints, as well as those of the local neighborhood around the endpoints. This allows for different types of neighborhoods in a graph, each with its own dynamics (e.…
Deep learning improves chaotic dynamics filtering without ensemble.
A neural network improves DOA estimation from a single snapshot.
We describe tests validating progress made toward acceleration and automation of hydrodynamic codes in the regime of developed turbulence by three Deep Learning (DL) Neural Network (NN) schemes trained on Direct Numerical Simulations of turbulence. Even the bare DL solutions, which do not take into account any physics …
Analysis of opinion dynamics in social networks plays an important role in today's life. For applications such as predicting users' political preference, it is particularly important to be able to analyze the dynamics of competing opinions. While observing the evolution of polar opinions of a social network's users ove…
Direction of arrival (DOA) estimation is a classical problem in signal processing with many practical applications. Its research has recently been advanced owing to the development of methods based on sparse signal reconstruction. While these methods have shown advantages over conventional ones, there are still difficu…
Bayesian method predicts future network configurations from past snapshots.
Ensemble method for fast portfolio valuation and risk management.