{"total":73,"rows":[{"id":"2203.06904","title":"Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models","created":"2022-03-14","cited_by_count":180,"area":null},{"id":"2312.10794","title":"A mathematical perspective on Transformers","created":"2023-12-17","cited_by_count":164,"area":null},{"id":"2106.13898","title":"Closed-form Continuous-time Neural Models","created":"2021-06-25","cited_by_count":65,"area":null},{"id":"2410.07064","title":"Data Selection via Optimal Control for Language Models","created":"2024-10-09","cited_by_count":38,"area":null},{"id":"2512.01868","title":"The Mean-Field Dynamics of Transformers","created":"2025-12-01","cited_by_count":30,"area":null},{"id":"2102.10801","title":"Neural Delay Differential Equations","created":"2021-02-22","cited_by_count":26,"area":null},{"id":"2102.01862","title":"Towards Robust Neural Networks via Close-loop Control","created":"2021-02-03","cited_by_count":23,"area":null},{"id":"2206.07335","title":"On Numerical Integration in Neural Ordinary Differential Equations","created":"2022-06-15","cited_by_count":21,"area":null},{"id":"2203.10378","title":"On Robust Prefix-Tuning for Text Classification","created":"2022-03-19","cited_by_count":15,"area":null},{"id":"2109.14158","title":"Second-Order Neural ODE Optimizer","created":"2021-09-29","cited_by_count":11,"area":null},{"id":"2202.04097","title":"Turnpike in optimal control of PDEs, ResNets, and beyond","created":"2022-02-08","cited_by_count":11,"area":null},{"id":"2109.09738","title":"An Optimal Control Framework for Joint-channel Parallel MRI Reconstruction without Coil Sensitivities","created":"2021-09-20","cited_by_count":10,"area":null},{"id":"2306.15630","title":"Coupling parameter and particle dynamics for adaptive sampling in Neural Galerkin schemes","created":"2023-06-27","cited_by_count":10,"area":null},{"id":"2105.01303","title":"Personalized Algorithm Generation: A Case Study in Learning ODE Integrators","created":"2021-05-04","cited_by_count":9,"area":null},{"id":"2205.09241","title":"Neural ODE Control for Trajectory Approximation of Continuity Equation","created":"2022-05-18","cited_by_count":9,"area":null},{"id":"2208.08707","title":"Deep Neural Network Approximation of Invariant Functions through Dynamical Systems","created":"2022-08-18","cited_by_count":9,"area":null},{"id":"2109.06294","title":"On the regularized risk of distributionally robust learning over deep neural networks","created":"2021-09-13","cited_by_count":8,"area":null},{"id":"2110.12393","title":"Deep Learning Approximation of Diffeomorphisms via Linear-Control Systems","created":"2021-10-24","cited_by_count":8,"area":null},{"id":"2203.10335","title":"TO-FLOW: Efficient Continuous Normalizing Flows with Temporal Optimization adjoint with Moving Speed","created":"2022-03-19","cited_by_count":8,"area":null},{"id":"2203.11758","title":"Linear convergence of a policy gradient method for some finite horizon continuous time control problems","created":"2022-03-22","cited_by_count":7,"area":null},{"id":"2211.14047","title":"On the Universal Approximation Property of Deep Fully Convolutional Neural Networks","created":"2022-11-25","cited_by_count":7,"area":null},{"id":"2401.03965","title":"Differential Equations for Continuous-Time Deep Learning","created":"2024-01-08","cited_by_count":7,"area":null},{"id":"2604.08580","title":"Adjoint Matching through the Lens of the Stochastic Maximum Principle in Optimal Control","created":"2026-03-28","cited_by_count":6,"area":null},{"id":"2102.13566","title":"Sparsity in long-time control of neural ODEs","created":"2021-02-26","cited_by_count":5,"area":null},{"id":"2105.03155","title":"Diffusion Mechanism in Residual Neural Network: Theory and Applications","created":"2021-05-07","cited_by_count":5,"area":null},{"id":"2206.12963","title":"Self-Healing Robust Neural Networks via Closed-Loop Control","created":"2022-06-26","cited_by_count":5,"area":null},{"id":"2106.10911","title":"Approximation capabilities of measure-preserving neural networks","created":"2021-06-21","cited_by_count":4,"area":null},{"id":"2201.00960","title":"Neural Piecewise-Constant Delay Differential Equations","created":"2022-01-04","cited_by_count":4,"area":null},{"id":"2206.12325","title":"ModLaNets: Learning Generalisable Dynamics via Modularity and Physical Inductive Bias","created":"2022-06-24","cited_by_count":4,"area":null},{"id":"2310.17584","title":"A minimax optimal control approach for robust neural ODEs","created":"2023-10-26","cited_by_count":4,"area":null},{"id":"2312.13807","title":"Cluster-based classification with neural ODEs via control","created":"2023-12-21","cited_by_count":4,"area":null},{"id":"2410.03924","title":"Online Control-Informed Learning","created":"2024-10-04","cited_by_count":4,"area":null},{"id":"2103.07405","title":"Optimal sequential decision making with probabilistic digital twins","created":"2021-03-12","cited_by_count":3,"area":null},{"id":"2307.02279","title":"From NeurODEs to AutoencODEs: a mean-field control framework for width-varying Neural Networks","created":"2023-07-05","cited_by_count":3,"area":null},{"id":"2404.00828","title":"PID Control-Based Self-Healing to Improve the Robustness of Large Language Models","created":"2024-03-31","cited_by_count":3,"area":null},{"id":"2409.19561","title":"Unifying back-propagation and forward-forward algorithms through model predictive control","created":"2024-09-29","cited_by_count":3,"area":null},{"id":"2508.01833","title":"Neural Predictive Control to Coordinate Discrete- and Continuous-Time Models for Time-Series Analysis with Control-Theoretical Improvements","created":"2025-08-03","cited_by_count":3,"area":null},{"id":"2603.09571","title":"An Optimal Control Approach To Transformer Training","created":"2026-03-10","cited_by_count":3,"area":null},{"id":"2101.03000","title":"On the Turnpike to Design of Deep Neural Nets: Explicit Depth Bounds","created":"2021-01-08","cited_by_count":2,"area":null},{"id":"2105.03788","title":"Dynamic Game Theoretic Neural Optimizer","created":"2021-05-08","cited_by_count":2,"area":null},{"id":"2112.05387","title":"Layer-Parallel Training of Residual Networks with Auxiliary-Variable Networks","created":"2021-12-10","cited_by_count":2,"area":null},{"id":"2203.13410","title":"Qualitative neural network approximation over R and C: Elementary proofs for analytic and polynomial activation","created":"2022-03-25","cited_by_count":2,"area":null},{"id":"2203.16874","title":"An Optimal Control Method to Compute the Most Likely Transition Path for Stochastic Dynamical Systems with Jumps","created":"2022-03-31","cited_by_count":2,"area":null},{"id":"2208.13006","title":"Neural Observer with Lyapunov Stability Guarantee for Uncertain Nonlinear Systems","created":"2022-08-27","cited_by_count":2,"area":null},{"id":"2209.05544","title":"The Mori-Zwanzig formulation of deep learning","created":"2022-09-12","cited_by_count":2,"area":null},{"id":"2306.01435","title":"Improving Adversarial Robustness of DEQs with Explicit Regulations Along the Neural Dynamics","created":"2023-06-02","cited_by_count":2,"area":null},{"id":"2309.04557","title":"Regret-Optimal Federated Transfer Learning for Kernel Regression with Applications in American Option Pricing","created":"2023-09-08","cited_by_count":2,"area":null},{"id":"2509.18404","title":"Zero-Shot Transferable Solution Method for Parametric Optimal Control Problems","created":"2025-09-22","cited_by_count":2,"area":null},{"id":"2111.08108","title":"Physics-informed neural networks via stochastic Hamiltonian dynamics learning","created":"2021-11-15","cited_by_count":1,"area":null},{"id":"2202.13800","title":"Differential equation and probability inspired graph neural networks for latent variable learning","created":"2022-02-28","cited_by_count":1,"area":null},{"id":"2209.10633","title":"Neural Generalized Ordinary Differential Equations with Layer-varying Parameters","created":"2022-09-21","cited_by_count":1,"area":null},{"id":"2311.10223","title":"Asymptotically Fair Participation in Machine Learning Models: an Optimal Control Perspective","created":"2023-11-16","cited_by_count":1,"area":null},{"id":"2405.19013","title":"On Dissipativity of Cross-Entropy Loss in Training ResNets","created":"2024-05-29","cited_by_count":1,"area":null},{"id":"2503.15105","title":"Control, Optimal Transport and Neural Differential Equations in Supervised Learning","created":"2025-03-19","cited_by_count":1,"area":null},{"id":"2507.06381","title":"KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks","created":"2025-07-08","cited_by_count":1,"area":null},{"id":"2512.18059","title":"Approximation and learning with compositional tensor trains","created":"2025-12-19","cited_by_count":1,"area":null},{"id":"2603.18331","title":"Understanding the Theoretical Foundations of Deep Neural Networks through Differential Equations","created":"2026-03-18","cited_by_count":1,"area":null},{"id":"2605.04230","title":"Layerwise LQR for Geometry-Aware Optimization of Deep Networks","created":"2026-05-05","cited_by_count":1,"area":null},{"id":"2106.13066","title":"Shallow Representation is Deep: Learning Uncertainty-aware and Worst-case Random Feature Dynamics","created":"2021-06-24","cited_by_count":0,"area":null},{"id":"2201.00801","title":"Revisiting PGD Attacks for Stability Analysis of Large-Scale Nonlinear Systems and Perception-Based Control","created":"2022-01-03","cited_by_count":0,"area":null},{"id":"2207.12242","title":"Multisymplectic Formulation of Deep Learning Using Mean--Field Type Control and Nonlinear Stability of Training Algorithm","created":"2022-07-07","cited_by_count":0,"area":null},{"id":"2304.05310","title":"Neural Delay Differential Equations: System Reconstruction and Image Classification","created":"2023-04-11","cited_by_count":0,"area":null},{"id":"2306.04228","title":"Data Mining for Faster, Interpretable Solutions to Inverse Problems: A Case Study Using Additive Manufacturing","created":"2023-06-07","cited_by_count":0,"area":null},{"id":"2404.05185","title":"Convergence analysis of controlled particle systems arising in deep learning: from finite to infinite sample size","created":"2024-04-08","cited_by_count":0,"area":null},{"id":"2404.19557","title":"Neural Dynamic Data Valuation via Stochastic State-Adjoint Trajectories","created":"2024-04-30","cited_by_count":0,"area":null},{"id":"2509.24223","title":"Semantic Editing with Coupled Stochastic Differential Equations","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2510.03303","title":"Machine Learning and Control: Foundations, Advances, and Perspectives","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2510.13134","title":"Convergence, design and training of continuous-time dropout as a random batch method","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2510.14168","title":"Optimal Control Theoretic Neural Optimizer: From Backpropagation to Dynamic Programming","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2603.13587","title":"State-space models through the lens of ensemble control","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2606.00469","title":"Constructive interpolation and generalization rates for neural ODEs: a control perspective","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.31397","title":"Mixture-of-Control: State-Aware Fine-Tuning for Transformer-based Models","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.27975","title":"Generalization Bounds on Optimal Control for Transformer Training and Wasserstein Distributional Robustness","created":"2026-07-30","cited_by_count":0,"area":null}],"next_cursor":null}