◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Anas Jnini

6 papers hereh-index 443 citations6 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • first author5
  • middle author1

Across the 6 of 6 papers where every author was matched, so the position is known.

fields
  • cs.LG3
  • cs.DC1
  • math.OC1
  • physics.flu-dyn1

identity via Semantic Scholar / OpenAlex

activity
20242026
most citedGauss-Newton Natural Gradient Descent for Physics-Informed Computational Fluid Dynamics

2 citations · 2 across the 2 of their papers we have counts for

collaborators
Showing cs.LGShow all

3 papers · 1 filter

cs.LG2026

Curvature-Aware Optimization for High-Accuracy Physics-Informed Neural Networks

Anas Jnini, Elham Kiyani, Khemraj Shukla +5

Efficient and robust optimization is essential for neural networks, enabling scientific machine learning models to converge rapidly to very high accuracy -- faithfully capturing co…

cs.LG2025

Dual Natural Gradient Descent for Scalable Training of Physics-Informed Neural Networks

Anas Jnini, Flavio Vella

Natural-gradient methods markedly accelerate the training of Physics-Informed Neural Networks (PINNs), yet their Gauss--Newton update must be solved in the parameter space, incurri…

cs.LG2025

Riemann Tensor Neural Networks: Learning Conservative Systems with Physics-Constrained Networks

Anas Jnini, Lorenzo Breschi, Flavio Vella

Divergence-free symmetric tensors (DFSTs) are fundamental in continuum mechanics, encoding conservation laws such as mass and momentum conservation. We introduce Riemann Tensor Neu…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.