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 “KRnet”

VAE-KRnet and its applications to variational Bayesstat.ML

Proposes VAE-KRnet for density estimation and variational Bayes.

problem Challenges of density estimation and posterior approximation in high dimensions.

method Combines VAE and KRnet for density estimation, incorporating mutual information maximization.

result Improves posterior approximation in high-dimensional cases.

VAE-KRnet density estimation variational Bayes mutual information dimensionality reduction

2020-06-29abs ↗pdf ↗

Augmented KRnet for density estimation and approximationstat.ML

Augmented KRnet improves flow-based generative modeling by maintaining exact invertibility.

problem Maintaining exact invertibility in flow-based generative models.

method Integrates augmented dimensions into KRnet to achieve full nonlinear updates in two iterations, keeping exact invertibility.

result Augmented KRnet achieves full nonlinear updates in two iterations, maintaining exact invertibility.

flow-based generative modeling KRnet exact invertibility augmented dimensions neural ODE

2021-05-26abs ↗pdf ↗

Dimension-reduced KRnet maps for high-dimensional Bayesian inverse problemsstat.ML

A new method maps high-dimensional Bayesian inverse problems to lower dimensions.

problem High-dimensional Bayesian inverse problems with complex prior information.

method Data-driven VAE prior and KRnet map for posterior approximation in latent space.

result Efficiently reduces computational cost and approximates posterior distributions.

Bayesian inverse problems dimension reduction KRnet variational autoencoder (VAE)latent space

2023-03-01abs ↗pdf ↗

Adaptive deep density approximation for Fokker-Planck equationsstat.ML

ADDA-KR uses KRnets for solving high-dimensional Fokker-Planck equations.

problem High-dimensional, unbounded Fokker-Planck equations.

method KRnet for density approximation, adaptive sampling for stochastic collocation.

result ADDA-KR efficiently approximates high-dimensional density functions.

Fokker-Planck equations density approximation KRnet adaptive sampling stochastic collocation

2021-03-20abs ↗pdf ↗

DAS-PINNs: A deep adaptive sampling method for solving high-dimensional partial differential equationsmath.NA

DAS-PINNs uses deep learning to solve complex PDEs more accurately.

problem Solving high-dimensional PDEs with high accuracy.

method Deep neural networks and generative models for adaptive sampling.

result DAS-PINNs significantly improves solution accuracy for low regularity and high-dimensional problems.

partial differential equations deep learning adaptive sampling neural networks generative models

2021-12-28abs ↗pdf ↗

Adaptive deep density approximation for stochastic dynamical systemsmath.NA

Adaptive neural network approximates stochastic system densities.

problem Approximating high-dimensional stochastic dynamical systems.

method Temporal KRnet (tKRnet) trained with adaptive collocation points and temporal decomposition.

result Improves density approximation for stochastic systems without curse of dimensionality.

stochastic dynamical systems deep neural networks density approximation Liouville equation adaptive training

2024-05-05abs ↗pdf ↗