Image de couverture de livre

Random weights of DNNs and emergence of fixed points

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Berlyand, L., Krupchytskyi, O., Slavin, V.
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence Numerical Analysis
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Quasi-Random Physics-informed Neural Networks
par: Yu, Tianchi, et autres
Publié: (2025)

Low-Rank Compression of Pretrained Models via Randomized Subspace Iteration
par: Pourkamali-Anaraki, Farhad
Publié: (2026)

On Stochastic Rounding with Few Random Bits
par: Fitzgibbon, Andrew, et autres
Publié: (2025)

Muon is Not That Special: Random or Inverted Spectra Work Just as Well
par: Shumaylov, Zakhar, et autres
Publié: (2026)

Minimisation of Quasar-Convex Functions Using Random Zeroth-Order Oracles
par: Farzin, Amir Ali, et autres
Publié: (2025)

Min-Max Optimisation for Nonconvex-Nonconcave Functions Using a Random Zeroth-Order Extragradient Algorithm
par: Farzin, Amir Ali, et autres
Publié: (2025)

Truncated Matrix Completion - An Empirical Study
par: Naik, Rishhabh, et autres
Publié: (2025)

BWLer: Barycentric Weight Layer Elucidates a Precision-Conditioning Tradeoff for PINNs
par: Liu, Jerry, et autres
Publié: (2025)

Deriving Transformer Architectures as Implicit Multinomial Regression
par: Actor, Jonas A., et autres
Publié: (2025)

Generalized Orders of Magnitude for Scalable, Parallel, High-Dynamic-Range Computation
par: Heinsen, Franz A., et autres
Publié: (2025)

GRAFT: Gradient-Aware Fast MaxVol Technique for Dynamic Data Sampling
par: Jha, Ashish, et autres
Publié: (2025)

KAN-GCN: Combining Kolmogorov-Arnold Network with Graph Convolution Network for an Accurate Ice Sheet Emulator
par: Liu, Zesheng, et autres
Publié: (2025)

Market-Driven Subset Selection for Budgeted Training
par: Jha, Ashish, et autres
Publié: (2025)

A Mathematical Explanation of Transformers
par: Tai, Xue-Cheng, et autres
Publié: (2025)

Beyond Loss Guidance: Using PDE Residuals as Spectral Attention in Diffusion Neural Operators
par: Sawhney, Medha, et autres
Publié: (2025)

STNet: Spectral Transformation Network for Solving Operator Eigenvalue Problem
par: Wang, Hong, et autres
Publié: (2025)

Mixed precision accumulation for neural network inference guided by componentwise forward error analysis
par: Arar, El-Mehdi El, et autres
Publié: (2025)

Branching Strategies Based on Subgraph GNNs: A Study on Theoretical Promise versus Practical Reality
par: Zhou, Junru, et autres
Publié: (2025)

Unveiling the Power of Multiple Gossip Steps: A Stability-Based Generalization Analysis in Decentralized Training
par: Li, Qinglun, et autres
Publié: (2025)

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

On Uniform Weighted Deep Polynomial approximation
par: Yeon, Kingsley, et autres
Publié: (2025)

DeepContour: A Hybrid Deep Learning Framework for Accelerating Generalized Eigenvalue Problem Solving via Efficient Contour Design
par: Chen, Yeqiu, et autres
Publié: (2025)

Guided Diffusion Sampling on Function Spaces with Applications to PDEs
par: Yao, Jiachen, et autres
Publié: (2025)

Monte Carlo-Type Neural Operator for Differential Equations
par: Choutri, Salah Eddine, et autres
Publié: (2025)

Accelerating Eigenvalue Dataset Generation via Chebyshev Subspace Filter
par: Wang, Hong, et autres
Publié: (2025)

Defining Foundation Models for Computational Science: A Call for Clarity and Rigor
par: Choi, Youngsoo, et autres
Publié: (2025)

CFO: Learning Continuous-Time PDE Dynamics via Flow-Matched Neural Operators
par: Hou, Xianglong, et autres
Publié: (2025)

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

Robust Non-Linear Correlations via Polynomial Regression
par: Giuliani, Luca, et autres
Publié: (2025)

Accelerated Gradient-based Design Optimization Via Differentiable Physics-Informed Neural Operator: A Composites Autoclave Processing Case Study
par: Patel, Janak M., et autres
Publié: (2025)

Quantum Neural Network Restatement of Markov Jump Process
par: Zarezadeh, Z., et autres
Publié: (2025)

Intrinsic Dimension Estimating Autoencoder (IDEA) Using CancelOut Layer and a Projected Loss
par: Oriou, Antoine, et autres
Publié: (2025)

Message-Passing GNNs Fail to Approximate Sparse Triangular Factorizations
par: Trifonov, Vladislav, et autres
Publié: (2025)

A Practical Approach to Causal Inference over Time
par: Cinquini, Martina, et autres
Publié: (2024)

A Mathematical Guide to Operator Learning
par: Boullé, Nicolas, et autres
Publié: (2023)

Learning to Discover Iterative Spectral Algorithms
par: Liu, Zihang, et autres
Publié: (2026)

Sparse $L^1$-Autoencoders for Scientific Data Compression
par: Chung, Matthias, et autres
Publié: (2024)

Graph Neural Networks for Emulation of Finite-Element Ice Dynamics in Greenland and Antarctic Ice Sheets
par: Koo, Younghyun, et autres
Publié: (2024)

Neural Operators with Localized Integral and Differential Kernels
par: Liu-Schiaffini, Miguel, et autres
Publié: (2024)

HomPINNs: homotopy physics-informed neural networks for solving the inverse problems of nonlinear differential equations with multiple solutions
par: Zheng, Haoyang, et autres
Publié: (2023)