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.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “NeuralODEs”

Gaussian processes meet NeuralODEs: A Bayesian framework for learning the dynamics of partially observed systems from scarce and noisy datacs.LG

GP-NODE combines Gaussian processes and NeuralODEs for Bayesian system identification.

problem Bayesian systems identification from partial, noisy and irregular observations.

method Differentiable programming, Hamiltonian Monte Carlo, Gaussian Process priors, sparsity-promoting priors.

result Efficient inference of posterior distributions over plausible models with quantified uncertainty.

Bayesian systems identification Gaussian processes NeuralODEs partial observations noisy data

2021-03-04abs ↗pdf ↗

Learning Continuous System Dynamics from Irregularly-Sampled Partial Observationscs.LG

Paper proposes learning system dynamics from irregularly-sampled partial observations.

problem Capturing dynamics of multi-agent systems with irregular and partial observations.

method LG-ODE, a latent ordinary differential equation model using graph neural networks and neuralODE.

result Demonstrates effectiveness on motion capture, spring system, and charged particle datasets.

system dynamics partial observations multi-agent systems graph neural networks neuralODE

2020-11-08abs ↗pdf ↗

CODE: A global approach to ODE dynamics learningcs.LG

CODE learns ODE dynamics from sparse data, outperforming neural and kernel methods.

problem Learning ODE dynamics from sparse and noisy data.

method CODE uses Polynomial Chaos Expansion (aPCE) for the ODE's RHS, enabling global orthonormal polynomial representation.

result CODE exhibits remarkable extrapolation capabilities even under novel initial conditions and measurement noise.

ODE learning sparse data sparse sampling Polynomial Chaos Expansion extrapolation

2025-11-19abs ↗pdf ↗

Balanced Neural ODEs: nonlinear model order reduction and Koopman operator approximationscs.LG

Balanced Neural ODEs combine VAEs and Neural ODEs for efficient time series modeling.

problem Efficiently modeling systems with time-varying inputs and varying complexity.

method Combines VAEs for dimensionality reduction and Neural ODEs for dynamics, using variational parameters to adaptively learn.

result Balanced Neural ODEs (B-NODE) efficiently approximate Koopman operator without predefined dimensionality.

Neural ODEs Variational Autoencoders Koopman operator Time series modeling Dimensionality reduction

2024-10-14abs ↗pdf ↗

Hamiltonian Mechanics of Feature Learning: Bottleneck Structure in Leaky ResNetsstat.ML

Study on feature learning in Leaky ResNets, explaining bottleneck structure.

problem Understanding feature learning in deep neural networks.

method Lagrangian and Hamiltonian reformulation of representation geodesics.

result Emergence of a bottleneck structure in large effective depth networks.

Leaky ResNets Feature Learning Hamiltonian Mechanics Representation Geodesics Bottleneck Structure

2024-05-27abs ↗pdf ↗

Adversarial Robustness of Stabilized NeuralODEs Might be from Obfuscated Gradientscs.LG

SONet stabilizes ODE networks for robustness without adversarial training.

problem Improving adversarial robustness of neural networks without sacrificing natural accuracy.

method SONet uses skew-symmetric ODE blocks and DOPRI5 solver for robustness.

result SONet achieves comparable robustness to adversarial defense methods without trade-off.

adversarial robustness Neural ODEs skew-symmetric DOPRI5 gradient masking

2020-09-28abs ↗pdf ↗