On-device research index

arXiv research

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.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

7 results for “ODE-RNN”

Cubic Spline Smoothing Compensation for Irregularly Sampled Sequencescs.LG

Cubic spline smoothing improves interpolation between irregularly sampled data.

problem Interpolation discontinuity in recurrent neural networks for irregularly sampled sequences.

method Cubic spline smoothing compensation module trained end-to-end with ODE-RNN.

result Improves interpolation between irregularly sampled data points.

Cubic spline ODE-RNN Interpolation Neural networks Irregular sampling

2020-10-03abs ↗pdf ↗

Latent ODEs for Irregularly-Sampled Time Seriescs.LG

Time series with non-uniform intervals occur in many applications, and are difficult to model using standard recurrent neural networks (RNNs). We generalize RNNs to have continuous-time hidden dynamics defined by ordinary differential equations (ODEs), a model we call ODE-RNNs. Furthermore, we use ODE-RNNs to replace t…

2019-07-08abs ↗pdf ↗

Neural Differential Recurrent Neural Network with Adaptive Time Stepsstat.ML

A neural RNN model adapts time steps for non-stationary time series data.

problem Modeling and forecasting non-stationary time series with sharp changes.

method RNN-ODE-Adap model using neural ODE and adaptive time steps.

result Consistent estimation of intensity function for Hawkes-type data.

neural ODE RNN adaptive time steps non-stationary time series Hawkes process

2023-06-02abs ↗pdf ↗

Latent Dynamical Implicit Diffusion Processescs.LG

Proposes LDIDPs for efficient sequential data generation from latent dynamical models.

problem Challenges in generating high-fidelity sequential samples from latent dynamical models.

method Utilizes implicit diffusion processes to sample from latent dynamical processes.

result Demonstrates accurate learning of dynamics and efficient generation of high-quality sequential data.

latent dynamical models diffusion processes sequential data implicit sampling neural decoding

2023-06-12abs ↗pdf ↗

SurvLatent ODE : A Neural ODE based time-to-event model with competing risks for longitudinal data improves cancer-associated Venous Thromboembolism (VTE) predictioncs.LG

SurvLatent ODE predicts VTE risk for cancer patients, outperforming current methods.

problem Predicting clinical outcomes from irregularly sampled EHR data with competing events.

method Neural ODE-based Recurrent Neural Networks (ODE-RNN) for flexible survival time estimation.

result SurvLatent ODE outperforms Khorana Risk scores for VTE risk prediction.

VTE prediction cancer neural ODE recurrent neural networks time-to-event

2022-04-20abs ↗pdf ↗

Neural Jump Ordinary Differential Equations: Consistent Continuous-Time Prediction and Filteringstat.ML

Neural Jump ODE improves continuous-time prediction and filtering of irregularly sampled time series.

problem Theoretical guarantees for continuous-time prediction and filtering of irregularly observed time series.

method Introducing Neural Jump ODE (NJ-ODE) that models conditional expectation between observations with neural ODEs and jumps.

result Theoretical guarantees for the

L^2

-optimal prediction are provided, showing convergence of model output to optimal prediction.

Neural ODE Continuous-time prediction Irregularly sampled time series Conditional expectation Jump process

2020-06-08abs ↗pdf ↗

The LOB Recreation Model: Predicting the Limit Order Book from TAQ History Using an Ordinary Differential Equation Recurrent Neural Networkq-fin.TR

Model recreates LOB from TAQ data for small-tick stocks.

problem Lack of LOB data makes market analysis difficult.

method Combines GRU and ODE-RNN to predict LOB volumes.

result Model accurately recreates LOB with high precision.

deep learning financial markets LOB recreation TAQ data replay model

2021-03-02abs ↗pdf ↗