Copertina

Latent-Space Mean-Field Theory for Deep BitNet-like Training: Constrained Gradient Flows with Smooth Quantization and STE Limits

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kim, Dongwon, Lee, Dongseok
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Optimization and Control
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Mean Field Game of Controls with State Reflections: Existence and Limit Theory
di: Bo, Lijun, et al.
Pubblicazione: (2025)

Multiobjective Accelerated Gradient-like Flow with Asymptotic Vanishing Normalized Gradient
di: Yin, Yingdong
Pubblicazione: (2025)

Toward a Unified Theory of Gradient Descent under Generalized Smoothness
di: Tyurin, Alexander
Pubblicazione: (2024)

Mean-Field Limits for Two-Layer Neural Networks Trained with Consensus-Based Optimization
di: De Deyn, William, et al.
Pubblicazione: (2025)

Control Barrier Function Based Design of Gradient Flows for Constrained Nonlinear Programming
di: Allibhoy, Ahmed, et al.
Pubblicazione: (2022)

The Mean-Field Limit of Online Stochastic Vector Balancing
di: Fiedler, Christian, et al.
Pubblicazione: (2026)

Deep Reinforcement Learning for Infinite Horizon Mean Field Problems in Continuous Spaces
di: Angiuli, Andrea, et al.
Pubblicazione: (2023)

Norm-Constrained Flows and Sign-Based Optimization: Theory and Algorithms
di: Leplat, Valentin, et al.
Pubblicazione: (2025)

Distributed Optimization with Finite Bit Adaptive Quantization for Efficient Communication and Precision Enhancement
di: Rikos, Apostolos I., et al.
Pubblicazione: (2024)

Stochastic Mean-Field LQ Stackelberg Differential Games with Random Coefficients: Theory and a Deep FBSDE Picard Solver
di: Yang, Ying, et al.
Pubblicazione: (2026)

High-dimensional Mean-Field Games by Particle-based Flow Matching
di: Yu, Jiajia, et al.
Pubblicazione: (2025)

Mean Field Games with Major and Minor Agents: the Limiting Problem and Nash Equilibrium
di: Huang, Ziyu, et al.
Pubblicazione: (2022)

A Total Variation Flow Scheme for Ergodic Mean Field Games
di: Kalise, Dante, et al.
Pubblicazione: (2024)

Deep Policy Iteration for High-Dimensional Mean Field Games
di: Assouli, Mouhcine, et al.
Pubblicazione: (2023)

Doubly Smoothed Optimistic Gradients: A Universal Approach for Smooth Minimax Problems
di: Zheng, Taoli, et al.
Pubblicazione: (2025)

Mean Field Game and Control for Switching Hybrid Systems
di: C., Tejaswi K., et al.
Pubblicazione: (2024)

State Constrained Optimal Control Problems With Control On The Acceleration. Applications To Kinetic Mean Field Games
di: Achdou, Yves
Pubblicazione: (2025)

Improved Performance of Stochastic Gradients with Gaussian Smoothing
di: Starnes, Andrew, et al.
Pubblicazione: (2023)

Gradient Descent for Convex and Smooth Noisy Optimization
di: Hu, Feifei, et al.
Pubblicazione: (2024)

Smoothed Proximal Lagrangian Method for Nonlinear Constrained Programs
di: Pu, Wenqiang, et al.
Pubblicazione: (2024)

Tight Lower Bounds for the Bit and Inner Product Oracle for Constrained Convex Optimization
di: Basu, Amitabh, et al.
Pubblicazione: (2025)

Cosine-Similarity Methods for Efficient Training and Sampling in High-Dimensional Latent Spaces
di: Duan, Xu, et al.
Pubblicazione: (2025)

Inertial Bregman Proximal Gradient under Partial Smoothness
di: Godeme, Jean-Jacques
Pubblicazione: (2025)

Adaptive Accelerated Gradient Method for Smooth Convex Optimization
di: Wang, Zepeng, et al.
Pubblicazione: (2025)

Decentralized Relaxed Smooth Optimization with Gradient Descent Methods
di: Jiang, Zhanhong, et al.
Pubblicazione: (2025)

Nonlinearly Preconditioned Gradient Methods under Generalized Smoothness
di: Oikonomidis, Konstantinos, et al.
Pubblicazione: (2025)

Quantization Of Probability Measures In Maximum~Mean~Discrepancy Distance
di: Mehraban, Zahra, et al.
Pubblicazione: (2025)

Clipped Stochastic Gradient Tracking For Locally Smooth Functions
di: Mei, Leilei, et al.
Pubblicazione: (2026)

The Geometry of Constrained Optimization: Constrained Gradient Flows via Reparameterization: A-Stable Implicit Schemes, KKT from Stationarity, and Geometry-Respecting Algorithms
di: Leplat, Valentin
Pubblicazione: (2025)

A Stochastic-Gradient-based Interior-Point Algorithm for Solving Smooth Bound-Constrained Optimization Problems
di: Curtis, Frank E., et al.
Pubblicazione: (2023)

Decentralized Exchangeable Stochastic Dynamic Teams in Continuous-time, their Mean-Field Limits and Optimality of Symmetric Policies
di: Sanjari, Sina, et al.
Pubblicazione: (2024)

An Extension of Major-Minor Mean Field Game Theory
di: González, Agustín Muñoz
Pubblicazione: (2026)

Information Geometry of Exponentiated Gradient: Convergence beyond L-Smoothness
di: Elshiaty, Yara, et al.
Pubblicazione: (2025)

Inexactly Smooth Performance Estimation and New Optimized Gradient Methods
di: Zoll, Aaron, et al.
Pubblicazione: (2026)

Generalized Stochastic Gradient Descent with Momentum Methods for Smooth Optimization
di: Wang, Zimeng, et al.
Pubblicazione: (2026)

Mirror Mean-Field Langevin Dynamics
di: Gu, Anming, et al.
Pubblicazione: (2025)

Convergence of Actor-Critic Learning for Mean Field Games and Mean Field Control in Continuous Spaces
di: Fouque, Jean-Pierre, et al.
Pubblicazione: (2025)

Power-Constrained Policy Gradient Methods for LQR
di: Verma, Ashwin, et al.
Pubblicazione: (2025)

Deep Galerkin Method for Mean Field Control Problem
di: Sun, Jingruo
Pubblicazione: (2022)

Variable Smoothing Alternating Proximal Gradient Algorithm for Coupled Composite Optimization
di: Long, Xian-Jun, et al.
Pubblicazione: (2025)