#PINNs
LightNews LightNews
How Do PINNs Work for Structural Simulation, and When Should Engineers Use Them? — https://aistructuralreview.com/knowledge/how_do_pinns_work_for_structural_simulation_and_when_should_engineers_use_them.php
How Do PINNs Work for Structural Simulation, and When Should Engineers Use Them?
September 28, 2026 at 10:42 AM
cslg-bot.bsky.social
Kejia Zhang, Youran Sun, Haizhao Yang: Staged Depth Training: A Representation Curriculum for PINNs https://arxiv.org/abs/2609.30299 https://arxiv.org/pdf/2609.30299 https://arxiv.org/html/2609.30299
September 28, 2026 at 6:42 AM
quantum-news.bsky.social
OQC, Citi, and NQCC Evaluate Quantum-Compressed PINNs for Financial Derivative Pricing Workflows

Read more:
https://quantumcomputingreport.com/oqc-citi-and-nqcc-evaluate-quantum-compressed-pinns-for-financial-derivative-pricing-workflows/
OQC, Citi, and NQCC Evaluate Quantum-Compressed PINNs for Financial Derivative Pricing Workflows - Quantum Computing Report
Quantum platform developer Oxford Quantum Circuits (OQC) has completed a joint technical case study in collaboration with global financial institution Citi and the UK’s National Quantum Computing Centre (NQCC).
quantumcomputingreport.com
September 23, 2026 at 2:20 AM
tmlr-pub.bsky.social
High precision PINNs in unbounded domains: application to singularity formulation in PDEs

Yixuan Wang, Ziming Liu, Zongyi Li, Anima Anandkumar, Thomas Y. Hou

Action editor: William Redman

https://openreview.net/forum?id=g34kZZAbT8

#singularities #singularity #pdes
September 22, 2026 at 8:20 AM
tmlr-pub.bsky.social
ProPINN: Demystifying Propagation Failures in Physics Informed Neural Networks

Yuezhou Ma, Haixu Wu, Hang Zhou, Huikun Weng, Jianmin Wang, Mingsheng Long

Action editor: Lei Feng

https://openreview.net/forum?id=Wy54lrFd46

#propagation #pinn #pinns
September 22, 2026 at 12:20 AM
physicsfludyn-bot.bsky.social
Michael Mommert, Marie-Christine Volk, Christian Bauer: An improved periodic activation for PINNs reconstructing convective flows https://arxiv.org/abs/2609.21798 https://arxiv.org/pdf/2609.21798 https://arxiv.org/html/2609.21798
September 21, 2026 at 6:57 AM
amaebooknew.bsky.social
Pythonで動かしながら学ぶ PINNs・科学機械学習入門: データと物理法則を融合して現象をモデル化する <アルゴ太郎> が、Kindleストアで予約開始されました。12/14(月)配信。
Pythonで動かしながら学ぶ PINNs・科学機械学習入門: データと物理法則を融合して現象をモデル化する
著者：アルゴ太郎(著)　個人出版　2026/12/14(月)配信
5leaf.jp
September 21, 2026 at 2:06 AM
behavecolpapers.bsky.social
Extended physics-informed neural networks (Ex-PINNs): a machine-learning method for solving partial differential equations in domain with spatially heterogeneous parameters SciReports
Extended physics-informed neural networks (Ex-PINNs): a machine-learning method for solving partial differential equations in domain with spatially heterogeneous parameters
Scientific Reports, Published online: 19 September 2026; doi:10.1038/s41598-026-72553-4Extended physics-informed neural networks (Ex-PINNs): a machine-learning method for solving partial differential equations in domain with spatially heterogeneous parameters
dlvr.it
September 19, 2026 at 7:29 PM
mathna-bot.bsky.social
Nilo Schwencke, Roland Maier: Beyond PINNs: A Unified Gauss--Newton and Petrov--Galerkin Framework for Neural and Hybrid PDE Solvers https://arxiv.org/abs/2609.20641 https://arxiv.org/pdf/2609.20641 https://arxiv.org/html/2609.20641
September 18, 2026 at 6:49 AM
trending-hi.bsky.social
पिछले 30 मिनट के विषय 🧭:

1. OQC 🆕
2. PINNs 🆕
3. उभर 🆕
4. जबक 🆕
5. QPINNs 🆕
6. Quantum 🆕
7. Carlo 🆕
8. आवश 🆕
9. यकत 🆕
10. करत 🌟
September 16, 2026 at 2:00 AM
informaq-pt.bsky.social
OQC e Trust Base avaliaram abordagens quânticas e híbridas para precificação de derivativos e fluxos de trabalho de risco. PINNs clássicas emergiram como práticas atualmente, enquanto QPINNs e Quantum Monte Carlo permanecem como direções de pesquisa valiosas exigindo melhorias...
Métodos Quânticos Híbridos para Finanças: Benchmarking de Precificação, Risco e Integração Quântico-Clássica
iq.fp2.dev
September 16, 2026 at 1:51 AM
informaq-he.bsky.social
OQC ו-Trust Base הערכו גישות קוונטיות והיברידיות לתמחור נגזרות וזרימות עבודה של ניהול סיכונים. PINNs קלאסיים התבררו כשימושיים בפועל כיום, בעוד QPINNs ו-Quantum Monte Carlo נותרים כיווני מחקר בעלי ערך הדורשים שיפורי חומרה והשתלבות הדוקה יותר...

#פיננסים_קוונטיים #שירותים_פיננסיים #חדשות
שיטות קוונטיום היברידיות בפיננסים: בדיקת ביצועים של תמחור, סיכון, והשילוב קוונטום-קלאסי
oqc.tech
September 16, 2026 at 1:51 AM
informaq-ar.bsky.social
قيّمت OQC و Trust Base الأساليب الكمية والهجينة لتسعير المشتقات وسير عمليات إدارة المخاطر. برزت شبكات PINNs الكلاسيكية كحل عملي في الوقت الحاضر، بينما تظل شبكات QPINNs وطريقة مونت كارلو الكمية اتجاهات بحثية قيمة تتطلب تحسينات الأجهزة والتكامل الأوثق...

#التمويل_الكمي #الخدمات_المالية #أخبار
الطرق الكمية الهجينة في التمويل: قياس معايير التسعير والمخاطر والتكامل الكمي-الكلاسيكي
oqc.tech
September 16, 2026 at 1:50 AM
informaq-vi.bsky.social
OQC và Trust Base đã đánh giá các phương pháp lượng tử và lai để định giá đạo hàm và quy trình quản lý rủi ro. PINNs cổ điển hiện đã nổi lên như là thực tế hôm nay, trong khi QPINNs và Phương pháp Monte Carlo Lượng tử vẫn là những hướng nghiên cứu có giá trị yêu cầu cải tiến p...
Phương pháp Lượng tử Lai cho Tài chính: Đánh giá Định giá, Rủi ro và Tích hợp Lượng tử-Cổ điển
oqc.tech
September 16, 2026 at 1:50 AM
informaq-th.bsky.social
OQC และ Trust Base ประเมินแนวทางควอนตัมและแบบไฮบริดสำหรับการกำหนดราคาตราสารอนุพันธ์และกระบวนการจัดการความเสี่ยง Classical PINNs ปรากฏว่าใช้งานได้จริงในปัจจุบัน ขณะที่ QPINNs และ Quantum Monte Carlo ยังคงเป็นทิศทางการวิจัยที่มีคุณค่าซึ่งต้องการการปรับปรุงฮาร์ดแวร์และการบูรณาการ...
วิธีควอนตัมแบบไฮบริดสำหรับการเงิน: การเปรียบเทียบการกำหนดราคา ความเสี่ยง และการบูรณาการควอนตัม-คลาสสิก
oqc.tech
September 16, 2026 at 1:49 AM
informaq-hi.bsky.social
OQC और Trust Base ने डेरिवेटिव मूल्य निर्धारण और जोखिम कार्यप्रवाह के लिए क्वांटम और हाइब्रिड दृष्टिकोणों का मूल्यांकन किया। शास्त्रीय PINNs आज व्यावहारिक के रूप में उभरे, जबकि QPINNs और Quantum Monte Carlo हार्डवेयर सुधार और अधिक निकट एकीकरण की आवश्यकता वाली मूल्यवान अनुसंधान...
वित्त के लिए हाइब्रिड क्वांटम विधियां: मूल्य निर्धारण, जोखिम और क्वांटम-शास्त्रीय एकीकरण की बेंचमार्किंग
oqc.tech
September 16, 2026 at 1:49 AM
informaq-de.bsky.social
OQC und Trust Base evaluierten Quanten- und Hybridansätze für die Preisgestaltung von Derivaten und Risikoarbeitsabläufe. Klassische PINNs erwiesen sich heute als praktisch, während QPINNs und Quantum Monte Carlo wertvolle Forschungsrichtungen bleiben, die Hardwareverbesserung...
Hybrid Quantenmethoden für Finanzen: Bewertung von Preisbildung, Risiko und Quantenklassischer Integration
oqc.tech
September 16, 2026 at 1:49 AM
informaq-fr.bsky.social
OQC et Trust Base ont évalué les approches quantiques et hybrides pour la tarification des dérivés et les flux de travail de gestion des risques. Les PINNs classiques se sont avérés pratiques aujourd'hui, tandis que les QPINNs et la méthode de Monte Carlo quantique restent des...
Méthodes quantiques hybrides pour la finance : évaluation comparative de la tarification, du risque et de l'intégration quantique-classique
oqc.tech
September 16, 2026 at 1:48 AM
informaq-es.bsky.social
OQC y Trust Base evaluaron enfoques cuánticos e híbridos para valoración de derivados y flujos de trabajo de riesgo. Los PINNs clásicos surgieron como prácticos hoy, mientras que los QPINNs y Monte Carlo Cuántico siguen siendo direcciones de investigación valiosas que requiere...
Métodos Cuánticos Híbridos para Finanzas: Evaluación de Precios, Riesgo e Integración Cuántico-Clásica
oqc.tech
September 16, 2026 at 1:48 AM
informaq-ja.bsky.social
OQCとTrust Baseは、デリバティブ価格設定とリスクワークフローに対する量子およびハイブリッドアプローチを評価しました。古典的PINNsは現在実用的であることが明らかになりましたが、QPINNsおよび量子モンテカルロ法は、ハードウェアの改善とより緊密な統合が必要とされる価値のある研究方向として残っています...

#量子金融 #金融サービス #ニュース
金融のためのハイブリッド量子手法：価格設定、リスク、および量子古典統合のベンチマーキング
oqc.tech
September 16, 2026 at 1:47 AM
informaq.bsky.social
OQC and Trust Base evaluated quantum and hybrid approaches for derivative pricing and risk workflows. Classical PINNs emerged as practical today, while QPINNs and Quantum Monte Carlo remain valuable research directions requiring hardware improvements and tighter integration st...
Hybrid Quantum Methods for Finance: Benchmarking Pricing, Risk, and Quantum-Classical Integration
iq.fp2.dev
September 16, 2026 at 1:46 AM
cslg-bot.bsky.social
Sidharth S. Menon, Irina Tezaur, Ameya D. Jagtap: Tackling Failure Modes of PINNs and PIKANs Using Conflict-Free Gradients https://arxiv.org/abs/2609.14841 https://arxiv.org/pdf/2609.14841 https://arxiv.org/html/2609.14841
September 15, 2026 at 6:44 AM
paperposterbot.bsky.social
arXiv📈🤖
Physics-informed machine learning: A mathematical framework with applications to time series forecasting
By Doum\`eche
Physics-informed machine learning (PIML) is an emerging framework that integrates physical knowledge into machine learning models. This physical prior often takes the form of a partial differential equation (PDE) system that the regression function must satisfy. In the first part of this dissertation, we analyze the statistical properties of PIML methods. In particular, we study the properties of physics-informed neural networks (PINNs) in terms of approximation, consistency, overfitting, and convergence. We then show how PIML problems can be framed as kernel methods, making it possible to apply the tools of kernel ridge regression to better understand their behavior. In addition, we use this kernel formulation to develop novel physics-informed algorithms and implement them efficiently on GPUs. The second part explores industrial applications in forecasting energy signals during atypical periods. We present results from the Smarter Mobility challenge on electric vehicle charging occupancy and examine the impact of mobility on electricity demand. Finally, we introduce a physics-constrained framework for designing and enforcing constraints in time series, applying it to load forecasting and tourism forecasting in various countries.
September 15, 2026 at 12:22 AM
scholarcast.bsky.social
New TurbRec: unsup. physics-consistent full-scale turbulence super-res. Low-res inputs + equations, no high-res data. Multi-scale Fourier embeddings; physics fixes small structures. Beats PINNs on spectra & stats.
link.springer.com/article/10.1...
#Turbulence #SuperRes #PhysicsInformedML
Physically-consistent full-scale unsupervised reconstruction in turbulent flow dynamics - Acta Mechanica Sinica
An advanced super-resolution reconstruction method for turbulent flows should be efficient, avoiding reliance on high-resolution data; reliable, strictly adhering to physical laws; and accurate, effec...
link.springer.com
September 14, 2026 at 11:07 AM
paperposterbot.bsky.social
arXiv📈🤖
PDE-constrained inverse problems at the $\sqrt{n}$ rate via debiased physics-informed neural networks
By Atchade, Mukherjee
We study the problem of estimating unknown parameters in PDE-constrained inverse problems from noisy observations, where the PDE solution is approximated using Physics-Informed Neural Networks (PINNs). While PINNs have demonstrated remarkable empirical success, existing estimators often inherit the slow nonparametric convergence rate of the neural-network solution, leading to biased and statistically inefficient inference for the finite-dimensional parameters of interest. To address this, we propose a two-step debiased estimation procedure that combines neural-network-based nonparametric estimation with an influence-function-based bias correction. By eliminating the first-order sensitivity of the estimator to errors in the nuisance function, our procedure yields a $\sqrt{n}$-consistent and asymptotically normal estimator without requiring undersmoothing of the neural network component. We further extend this framework to Bayesian inference by replacing the original likelihood with a debiased quasi-likelihood and establish a Bernstein-von Mises theorem showing that the resulting posterior contracts at the $\sqrt{n}$-rate with an asymptotic covariance matching that of the frequentist estimator. As a by-product of our analysis, we establish near-minimax optimal convergence rates for estimating a nonparametric regression function and its derivatives in Sobolev spaces using neural networks. Extensive numerical experiments corroborate our theoretical findings and demonstrate the necessity of the proposed debiasing procedure for valid statistical inference in PDE-constrained inverse problems.
September 14, 2026 at 6:50 AM