Image de couverture de livre

Convergent Stochastic Training of Attention and Understanding LoRA

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sun, Zhengkai, Kumar, Dibyakanti, Frangi, Alejandro F, Mukherjee, Anirbit, Sun, Mingfei
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Functional Analysis Probability
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Langevin Monte-Carlo Provably Learns Depth Two Neural Nets at Any Size and Data
par: Kumar, Dibyakanti, et autres
Publié: (2025)

Generalization Bounds for Physics-Informed Neural Networks for the Incompressible Navier-Stokes Equations
par: Andre-Sloan, Sebastien, et autres
Publié: (2026)

Investigating the Ability of PINNs To Solve Burgers' PDE Near Finite-Time BlowUp
par: Kumar, Dibyakanti, et autres
Publié: (2023)

Towards Size-Independent Generalization Bounds for Deep Operator Nets
par: Gopalani, Pulkit, et autres
Publié: (2022)

Convergence rate of Tsallis entropic regularized optimal transport
par: Suguro, Takeshi, et autres
Publié: (2023)

Stochastic approximation in infinite dimensions
par: Karandikar, Rajeeva Laxman, et autres
Publié: (2024)

Gaussian Processes with Sample Paths in Reproducing Kernel Banach Spaces
par: Karvonen, Toni, et autres
Publié: (2026)

Bayesian Optimization through Gaussian Cox Process Models for Spatio-temporal Data
par: Mei, Yongsheng, et autres
Publié: (2024)

Does the Barron space really defy the curse of dimensionality?
par: Schavemaker, Olov
Publié: (2025)

Distributionally robust approximation property of neural networks
par: Ceylan, Mihriban, et autres
Publié: (2025)

Smoothed Distance Kernels for MMDs and Applications in Wasserstein Gradient Flows
par: Rux, Nicolaj, et autres
Publié: (2025)

Distribution-Free Stochastic Analysis and Robust Multilevel Vector Field Anomaly Detection
par: Castrillon-Candas, Julio E, et autres
Publié: (2022)

An Interpretable Approach to Load Profile Forecasting in Power Grids using Galerkin-Approximated Koopman Pseudospectra
par: Tavasoli, Ali, et autres
Publié: (2023)

Poincaré Inequality for Local Log-Polyak-Lojasiewicz Measures : Non-asymptotic Analysis in Low-temperature Regime
par: Gong, Yun, et autres
Publié: (2025)

Constructive Approximation under Carleman's Condition, with Applications to Smoothed Analysis
par: Koehler, Frederic, et autres
Publié: (2025)

Sharp Matrix Empirical Bernstein Inequalities
par: Wang, Hongjian, et autres
Publié: (2024)

Hoeffding decomposition of black-box models with dependent inputs
par: Idrissi, Marouane Il, et autres
Publié: (2023)

Neural Hilbert Ladders: Multi-Layer Neural Networks in Function Space
par: Chen, Zhengdao
Publié: (2023)

Distributional Convergence of the Empirical Laplacians with Integral Kernels on Domains with Boundaries
par: Akwei, Bernard, et autres
Publié: (2025)

Stochastic dynamics on evolving geometric graphs
par: Daletskii, Alexei, et autres
Publié: (2025)

Stein's Method for Convergence Rates of Invariant Measures in the Nonlocal-to-Local Limit
par: Wu, Mingyan, et autres
Publié: (2026)

Wasserstein Contraction of Coordinate Ascent Variational Inference
par: Caprio, Rocco, et autres
Publié: (2026)

Stochastic proof of the sharp symmetrized Talagrand inequality
par: Courtade, Thomas A., et autres
Publié: (2024)

Stochastic evolution equations with Wick-analytic nonlinearities
par: Levajkovic, Tijana, et autres
Publié: (2023)

Stochastic dynamics of particle systems on unbounded degree graphs
par: Chargaziya, Georgy, et autres
Publié: (2023)

Convergence of non-reversible Markov processes via lifting and flow Poincar{é} inequality
par: Eberle, Andreas, et autres
Publié: (2025)

Minimum Norm Interpolation via The Local Theory of Banach Spaces: The Role of $2$-Uniform Convexity
par: Kur, Gil, et autres
Publié: (2026)

Pointwise Generalization in Deep Neural Networks
par: Li, Shaojie, et autres
Publié: (2026)

Size Lowerbounds for Deep Operator Networks
par: Mukherjee, Anirbit, et autres
Publié: (2023)

Stochastic Clock Attention for Aligning Continuous and Ordered Sequences
par: Soh, Hyungjoon, et autres
Publié: (2025)

Understanding two-scale criteria for Poincaré and log-Sobolev inequalities in the Euclidean case through Φ-entropies
par: Srinivasan, Vishwak
Publié: (2025)

Stochastic dynamics and the Polchinski equation: an introduction
par: Bauerschmidt, Roland, et autres
Publié: (2023)

Zeroth-order Logconcave Sampling
par: Kook, Yunbum, et autres
Publié: (2025)

Convergence of permuted products of exponentials
par: Anshelevich, Michael, et autres
Publié: (2025)

Regularized Gradient Clipping Provably Trains Wide and Deep Neural Networks
par: Tucat, Matteo, et autres
Publié: (2024)

Stochastic Localization with Non-Gaussian Tilts and Applications to Tensor Ising Models
par: Mikulincer, Dan, et autres
Publié: (2024)

Convergence Analysis of Max-Min Exponential Neural Network Operators in Orlicz Space
par: Pradhan, Satyaranjan, et autres
Publié: (2025)

Modified Equations for Stochastic Optimization
par: Perko, Stefan
Publié: (2025)

Riemannian Langevin Dynamics: Strong Convergence of Geometric Euler-Maruyama Scheme
par: Zhan, Zhiyuan, et autres
Publié: (2026)

Understanding Transfer Learning via Mean-field Analysis
par: Aminian, Gholamali, et autres
Publié: (2024)