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

3 results for “mesh-invariant”

GeONet: a neural operator for learning the Wasserstein geodesiccs.LG

GeONet learns the Wasserstein geodesic without mesh discretization.

problem Computing the Wasserstein geodesic between complex data distributions.

method Mesh-invariant deep neural operator network that learns saddle point optimality conditions.

result GeONet achieves comparable accuracy to standard OT solvers with reduced computational cost.

optimal transport geodesic neural operator mesh-invariant saddle point

2022-09-28abs ↗pdf ↗

The Random Feature Model for Input-Output Maps between Banach Spacesmath.NA

Random feature model approximates PDE solutions efficiently.

problem Approximating solutions to PDEs with high-dimensional inputs and outputs.

method Random feature model applied to infinite-dimensional operators.

result Efficient and accurate approximation of PDE solutions.

random feature model PDEs Banach spaces mesh-invariant approximation error

2020-05-20abs ↗pdf ↗

Machine learning assisted state prediction of misspecified linear dynamical system via modal reductionstat.ML

Framework corrects model form errors in structural dynamics predictions.

problem Model form errors in parametric models of structural dynamics.

method Gaussian Process Latent Force Model (GPLFM) for non-parametric discrepancy representation, linear Bayesian filtering for state and discrepancy estimation, modal reduction for computational tractability.

result Significant reduction of displacement and rotation prediction errors under unseen excitations.

structural dynamics model form errors Bayesian filtering modal reduction Gaussian Process Latent Force Model

2026-01-08abs ↗pdf ↗