Copertina

V-ABFT: Variance-Based Adaptive Threshold for Fault-Tolerant Matrix Multiplication in Mixed-Precision Deep Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Gao, Yiheng, Hua, Qin, Chen, Zizhong
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence Numerical Analysis
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Intrinsic Numerical Robustness and Fault Tolerance in a Neuromorphic Algorithm for Scientific Computing
di: Theilman, Bradley H., et al.
Pubblicazione: (2026)

DeepContour: A Hybrid Deep Learning Framework for Accelerating Generalized Eigenvalue Problem Solving via Efficient Contour Design
di: Chen, Yeqiu, et al.
Pubblicazione: (2025)

Deep Learning-Enhanced Preconditioning for Efficient Conjugate Gradient Solvers in Large-Scale PDE Systems
di: Li, Rui, et al.
Pubblicazione: (2024)

Truncated Matrix Completion - An Empirical Study
di: Naik, Rishhabh, et al.
Pubblicazione: (2025)

Quasi-Framelets: Robust Graph Neural Networks via Adaptive Framelet Convolution
di: Yang, Mengxi, et al.
Pubblicazione: (2022)

Unveiling the Power of Multiple Gossip Steps: A Stability-Based Generalization Analysis in Decentralized Training
di: Li, Qinglun, et al.
Pubblicazione: (2025)

ELM-DeepONets: Backpropagation-Free Training of Deep Operator Networks via Extreme Learning Machines
di: Son, Hwijae
Pubblicazione: (2025)

Scaling physics-informed hard constraints with mixture-of-experts
di: Chalapathi, Nithin, et al.
Pubblicazione: (2024)

PRISM: Distribution-free Adaptive Computation of Matrix Functions for Accelerating Neural Network Training
di: Yang, Shenghao, et al.
Pubblicazione: (2026)

Accelerating Matrix Diagonalization through Decision Transformers with Epsilon-Greedy Optimization
di: Bhatta, Kshitij, et al.
Pubblicazione: (2024)

Towards Faster Matrix Diagonalization with Graph Isomorphism Networks and the AlphaZero Framework
di: Zollicoffer, Geigh, et al.
Pubblicazione: (2024)

BWLer: Barycentric Weight Layer Elucidates a Precision-Conditioning Tradeoff for PINNs
di: Liu, Jerry, et al.
Pubblicazione: (2025)

Mixed precision accumulation for neural network inference guided by componentwise forward error analysis
di: Arar, El-Mehdi El, et al.
Pubblicazione: (2025)

On Uniform Weighted Deep Polynomial approximation
di: Yeon, Kingsley, et al.
Pubblicazione: (2025)

SPIKE: Stable Physics-Informed Kernel Evolution Method for Solving Hyperbolic Conservation Laws
di: Su, Hua, et al.
Pubblicazione: (2025)

Solving PDEs With Deep Neural Nets under General Boundary Conditions
di: Zhang, Chenggong
Pubblicazione: (2025)

Advancing the Understanding of Fixed Point Iterations in Deep Neural Networks: A Detailed Analytical Study
di: Ke, Yekun, et al.
Pubblicazione: (2024)

A Mathematical Guide to Operator Learning
di: Boullé, Nicolas, et al.
Pubblicazione: (2023)

Learning to Discover Iterative Spectral Algorithms
di: Liu, Zihang, et al.
Pubblicazione: (2026)

Stable Weight Updating: A Key to Reliable PDE Solutions Using Deep Learning
di: Noorizadegan, A., et al.
Pubblicazione: (2024)

ProFlow: Zero-Shot Physics-Consistent Sampling via Proximal Flow Guidance
di: Yu, Zichao, et al.
Pubblicazione: (2026)

Projection Methods for Operator Learning and Universal Approximation
di: Zappala, Emanuele
Pubblicazione: (2024)

Mixture of Experts Softens the Curse of Dimensionality in Operator Learning
di: Kratsios, Anastasis, et al.
Pubblicazione: (2024)

Learning from Integral Losses in Physics Informed Neural Networks
di: Saleh, Ehsan, et al.
Pubblicazione: (2023)

Kinetic-based regularization: Learning spatial derivatives and PDE applications
di: Ganguly, Abhisek, et al.
Pubblicazione: (2026)

Why Does Stochastic Gradient Descent Slow Down in Low-Precision Training?
di: Yun, Vincent-Daniel
Pubblicazione: (2025)

Critical Sampling for Robust Evolution Operator Learning of Unknown Dynamical Systems
di: Zhang, Ce, et al.
Pubblicazione: (2023)

Branching Strategies Based on Subgraph GNNs: A Study on Theoretical Promise versus Practical Reality
di: Zhou, Junru, et al.
Pubblicazione: (2025)

Autoregression-Free Neural Operators for Time-Dependent PDEs
di: Zhang, Jiaquan, et al.
Pubblicazione: (2026)

Leveraging Gauge Freedom for Learning Non-Gradient Population Dynamics of Stochastic Systems
di: Berman, Jules, et al.
Pubblicazione: (2026)

Learning Semilinear Neural Operators : A Unified Recursive Framework For Prediction And Data Assimilation
di: Singh, Ashutosh, et al.
Pubblicazione: (2024)

CFO: Learning Continuous-Time PDE Dynamics via Flow-Matched Neural Operators
di: Hou, Xianglong, et al.
Pubblicazione: (2025)

Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System Instances
di: Khodak, Mikhail, et al.
Pubblicazione: (2023)

eXmY: A Data Type and Technique for Arbitrary Bit Precision Quantization
di: Agrawal, Aditya, et al.
Pubblicazione: (2024)

Physics-Informed Neural Networks for High-Frequency and Multi-Scale Problems using Transfer Learning
di: Mustajab, Abdul Hannan, et al.
Pubblicazione: (2024)

AlgoFormer: An Efficient Transformer Framework with Algorithmic Structures
di: Gao, Yihang, et al.
Pubblicazione: (2024)

Principled Approaches for Extending Neural Architectures to Function Spaces for Operator Learning
di: Berner, Julius, et al.
Pubblicazione: (2025)

Mathematical Introduction to Deep Learning: Methods, Implementations, and Theory
di: Jentzen, Arnulf, et al.
Pubblicazione: (2023)

Core-Halo Decomposition: Decentralizing Large-Scale Fixed-Point Problems
di: Haixiang, et al.
Pubblicazione: (2026)

IFNSO: Iteration-Free Newton-Schulz Orthogonalization
di: Hu, Chen, et al.
Pubblicazione: (2026)