Cover Image

An Optimal Control Approach To Transformer Training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Akman, Kağan, Saldı, Naci, Yüksel, Serdar
Format:	Preprint
Published:	2026
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

Kernel Mean Embedding Topology: Weak and Strong Forms for Stochastic Kernels and Implications for Model Learning
by: Saldi, Naci, et al.
Published: (2025)

Optimality of Symmetric Independent Policies under Decentralized Mean-Field Information Sharing for Stochastic Teams and Equivalence with McKean-Vlasov Control of a Representative Agent
by: Sanjari, Sina, et al.
Published: (2024)

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

Quantum Markov Decision Processes: Dynamic and Semi-Definite Programs for Optimal Solutions
by: Saldi, Naci, et al.
Published: (2024)

Decentralized Detection with Many Sensors: Optimality of Exchangeable and Identical Encoding Policies
by: Sanjari, Sina, et al.
Published: (2025)

Quantum Markov Decision Processes: General Theory, Approximations, and Classes of Policies
by: Saldi, Naci, et al.
Published: (2024)

Mean-Field Systems with Heterogeneous Subteams: Optimality of Cluster-Symmetric Independent Policies and Equivalence with Decentralized McKean-Vlasov Control of Cluster-Representative Agents
by: Braun, Connor S., et al.
Published: (2026)

Maximum Causal Entropy IRL in Mean-Field Games and GNEP Framework for Forward RL
by: Anahtarci, Berkay, et al.
Published: (2024)

Robustness and Approximation of Discrete-time Mean-field Games under Discounted Cost Criterion
by: Aydın, Uğur, et al.
Published: (2023)

Another Look at Partially Observed Optimal Stochastic Control: Existence, Ergodicity, and Approximations without Belief-Reduction
by: Yüksel, Serdar
Published: (2023)

Quantizer Design for Finite Model Approximations, Model Learning, and Quantized Q-Learning for MDPs with Unbounded Spaces
by: Bicer, Osman, et al.
Published: (2025)

Existence of $ε$-Nash Equilibria in Nonzero-Sum and Zero-Sum Markov Games with Standard Borel Spaces via Finite Model Approximations
by: Saldi, Naci, et al.
Published: (2024)

Approximation of Discrete-Time Infinite-Horizon Mean-Field Equilibria via Finite-Horizon Mean-Field Equilibria
by: Aydın, Uğur, et al.
Published: (2025)

Partially Observed Optimal Stochastic Control: Regularity, Optimality, Approximations, and Learning
by: Kara, Ali Devran, et al.
Published: (2024)

On Borkar and Young Relaxed Control Topologies and Continuous Dependence of Invariant Measures on Control Policy
by: Yüksel, Serdar
Published: (2023)

Satisficing Paths and Independent Multi-Agent Reinforcement Learning in Stochastic Games
by: Yongacoglu, Bora, et al.
Published: (2021)

Reinforcement Learning for Jointly Optimal Coding and Control Policies for a Controlled Markovian System over a Communication Channel
by: Hubbard, Evelyn, et al.
Published: (2024)

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

Decentralized Learning for Optimality in Stochastic Dynamic Teams and Games with Local Control and Global State Information
by: Yongacoglu, Bora, et al.
Published: (2019)

Kernel Based Maximum Entropy Inverse Reinforcement Learning for Mean-Field Games
by: Anahtarci, Berkay, et al.
Published: (2025)

Data-Driven Non-Parametric Model Learning and Adaptive Control of MDPs with Borel spaces: Identifiability and Near Optimal Design
by: Mrani-Zentar, Omar, et al.
Published: (2025)

Towards an Optimal Control Perspective of ResNet Training
by: Püttschneider, Jens, et al.
Published: (2025)

SLAM as a Stochastic Control Problem with Partial Information: Optimal Solutions and Rigorous Approximations
by: Gusija, Ilir, et al.
Published: (2026)

An Optimal Transport Approach for Computing Adversarial Training Lower Bounds in Multiclass Classification
by: Trillos, Nicolas Garcia, et al.
Published: (2024)

Robust Decentralized Control of Coupled Systems via Risk Sensitive Control of Decoupled or Simple Models with Measure Change
by: Selk, Zachary, et al.
Published: (2024)

Best Ergodic Averages via Optimal Graph Filters in Reversible Markov Chains
by: Saldi, Naci
Published: (2024)

A Guaranteed-Stable Neural Network Approach for Optimal Control of Nonlinear Systems
by: Li, Anran, et al.
Published: (2025)

Kernel-Based Optimal Control: An Infinitesimal Generator Approach
by: Bevanda, Petar, 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)

Near Optimal Approximations and Finite Memory Policies for POMPDs with Continuous Spaces
by: Kara, Ali Devran, et al.
Published: (2024)

Nonconvex Optimization Framework for Group-Sparse Feedback Linear-Quadratic Optimal Control: Penalty Approach
by: Feng, Lechen, et al.
Published: (2025)

Nonconvex Optimization Framework for Group-Sparse Feedback Linear-Quadratic Optimal Control: Non-Penalty Approach
by: Feng, Lechen, et al.
Published: (2025)

An Optimal Transport Approach for Network Regression
by: Zalles, Alex G., et al.
Published: (2024)

Subjective Equilibria under Beliefs of Exogenous Uncertainty: Linear Quadratic Case
by: Arslan, Gürdal, et al.
Published: (2024)

Near-Optimal Real-Time Personalization with Simple Transformers
by: An, Lin, et al.
Published: (2025)

Q-Learning for Stochastic Control under General Information Structures and Non-Markovian Environments
by: Kara, Ali Devran, et al.
Published: (2023)

Optimal Push and Pull-Based Edge Caching For Dynamic Content
by: Abolhassani, Bahman, et al.
Published: (2024)

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

A Mathematical Programming Approach to Optimal Classification Forests
by: Blanco, Víctor, et al.
Published: (2022)

Refined Bounds on Near Optimality Finite Window Policies in POMDPs and Their Reinforcement Learning
by: Demirci, Yunus Emre, et al.
Published: (2024)