Cover Image

Sparse Transformer Architectures via Regularized Wasserstein Proximal Operator with $L_1$ Prior

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Han, Fuqun, Osher, Stanley, Li, Wuchen
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Optimization and Control
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Preconditioned Regularized Wasserstein Proximal Sampling
by: Tan, Hong Ye, et al.
Published: (2025)

Tensor train based sampling algorithms for approximating regularized Wasserstein proximal operators
by: Han, Fuqun, et al.
Published: (2024)

Accelerated Regularized Wasserstein Proximal Sampling Algorithms
by: Tan, Hong Ye, et al.
Published: (2026)

Splitting Regularized Wasserstein Proximal Algorithms for Nonsmooth Sampling Problems
by: Han, Fuqun, et al.
Published: (2025)

Convergence of Noise-Free Sampling Algorithms with Regularized Wasserstein Proximals
by: Han, Fuqun, et al.
Published: (2024)

A Natural Primal-Dual Hybrid Gradient Method for Adversarial Neural Network Training on Solving Partial Differential Equations
by: Liu, Shu, et al.
Published: (2024)

Score-based Neural Ordinary Differential Equations for Computing Mean Field Control Problems
by: Zhou, Mo, et al.
Published: (2024)

Numerical Analysis on Neural Network Projected Schemes for Approximating One Dimensional Wasserstein Gradient Flows
by: Zuo, Xinzhe, et al.
Published: (2024)

Gradient-adjusted underdamped Langevin dynamics for sampling
by: Zuo, Xinzhe, et al.
Published: (2024)

Optimal Control for Transformer Architectures: Enhancing Generalization, Robustness and Efficiency
by: Kan, Kelvin, et al.
Published: (2025)

Locally Regularized Sparse Graph by Fast Proximal Gradient Descent
by: Sun, Dongfang, et al.
Published: (2024)

Efficient Computation of Mean field Control based Barycenters from Reaction-Diffusion Systems
by: Vijaywargiya, Arjun, et al.
Published: (2024)

On Generalization and Regularization via Wasserstein Distributionally Robust Optimization
by: Wu, Qinyu, et al.
Published: (2022)

Numerical analysis of a first-order computational algorithm for reaction-diffusion equations via the primal-dual hybrid gradient method
by: Liu, Shu, et al.
Published: (2024)

End-to-End Training of High-Dimensional Optimal Control with Implicit Hamiltonians via Jacobian-Free Backpropagation
by: Gelphman, Eric, et al.
Published: (2025)

A Primal-dual hybrid gradient method for solving optimal control problems and the corresponding Hamilton-Jacobi PDEs
by: Meng, Tingwei, et al.
Published: (2024)

Convergence Analysis of the Wasserstein Proximal Algorithm beyond Geodesic Convexity
by: Zhu, Shuailong, et al.
Published: (2025)

Inexact Proximal Point Algorithms for Zeroth-Order Global Optimization
by: Zhang, Minxin, et al.
Published: (2024)

Zero-Shot Transferable Solution Method for Parametric Optimal Control Problems
by: Li, Xingjian, et al.
Published: (2025)

Stability of Transformers under Layer Normalization
by: Kan, Kelvin, et al.
Published: (2025)

Proximal Operators of Sorted Nonconvex Penalties
by: Gagneux, Anne, et al.
Published: (2025)

Sparse Deep Learning Models with the $\ell_1$ Regularization
by: Shen, Lixin, et al.
Published: (2024)

Operator Splitting for Learning to Predict Equilibria in Convex Games
by: McKenzie, Daniel, et al.
Published: (2021)

A New Convergence Analysis of Plug-and-Play Proximal Gradient Descent Under Prior Mismatch
by: Xu, Guixian, et al.
Published: (2026)

PINS: Proximal Iterations with Sparse Newton and Sinkhorn for Optimal Transport
by: Wu, Di, et al.
Published: (2025)

A Proximal Modified Quasi-Newton Method for Nonsmooth Regularized Optimization
by: Diouane, Youssef, et al.
Published: (2024)

A deep learning algorithm for computing mean field control problems via forward-backward score dynamics
by: Zhou, Mo, et al.
Published: (2024)

On the Stochastic (Variance-Reduced) Proximal Gradient Method for Regularized Expected Reward Optimization
by: Liang, Ling, et al.
Published: (2024)

A Unifying View of Anchoring via Operator-Side Tikhonov Regularization
by: Chen, Zihao
Published: (2026)

SPP-SBL: Space-Power Prior Sparse Bayesian Learning for Block Sparse Recovery
by: Zhang, Yanhao, et al.
Published: (2025)

Optimal transport natural gradient for statistical manifolds with continuous sample space
by: Chen, Yifan, et al.
Published: (2018)

Collaborative Bayesian Optimization via Wasserstein Barycenters
by: Zhan, Donglin, et al.
Published: (2025)

Universal Architectures for the Learning of Polyhedral Norms and Convex Regularizers
by: Unser, Michael, et al.
Published: (2025)

Flowing Datasets with Wasserstein over Wasserstein Gradient Flows
by: Bonet, Clément, et al.
Published: (2025)

Simulating Fokker-Planck equations via mean field control of score-based normalizing flows
by: Zhou, Mo, et al.
Published: (2025)

Conditional Sampling via Wasserstein Autoencoders and Triangular Transport
by: Al-Jarrah, Mohammad, et al.
Published: (2026)

Smoothing the Edges: Smooth Optimization for Sparse Regularization using Hadamard Overparametrization
by: Kolb, Chris, et al.
Published: (2023)

Dynamic Proximal Gradient Algorithms for Schatten-$p$ Quasi-Norm Regularized Problems
by: Shen, Weiping, et al.
Published: (2026)

Worst-case generation via minimax optimization in Wasserstein space
by: Cheng, Xiuyuan, et al.
Published: (2025)

Incremental Learning of Sparse Attention Patterns in Transformers
by: Yüksel, Oğuz Kaan, et al.
Published: (2026)