Statistical Learning Theory for Control: A Finite Sample Perspective
暂无分享,去创建一个
[1] A. Proutière,et al. Finite-Time Identification of Linear Systems: Fundamental Limits and Optimal Algorithms , 2023, IEEE Transactions on Automatic Control.
[2] Ingvar M. Ziemann. A note on the smallest eigenvalue of the empirical covariance of causal Gaussian processes , 2022, ArXiv.
[3] M. Fazel,et al. Towards a Theoretical Foundation of Policy Optimization for Learning Control Policies , 2022, ArXiv.
[4] Stephen Tu,et al. Learning with little mixing , 2022, NeurIPS.
[5] N. Matni,et al. How are policy gradient methods affected by the limits of control? , 2022, 2022 IEEE 61st Conference on Decision and Control (CDC).
[6] Stephen Tu,et al. TaSIL: Taylor Series Imitation Learning , 2022, NeurIPS.
[7] George J. Pappas,et al. Learning to Control Linear Systems can be Hard , 2022, COLT.
[8] Samet Oymak,et al. Revisiting Ho–Kalman-Based System Identification: Robustness and Finite-Sample Analysis , 2022, IEEE Transactions on Automatic Control.
[9] Stephen Tu,et al. Learning from many trajectories , 2022, ArXiv.
[10] N. Matni,et al. Single Trajectory Nonparametric Learning of Nonlinear Dynamics , 2022, COLT.
[11] Boualem Djehiche,et al. Efficient learning of hidden state LTI state space models of unknown order , 2022, 2202.01625.
[12] H. Sandberg,et al. Regret Lower Bounds for Learning Linear Quadratic Gaussian Systems , 2022, ArXiv.
[13] Yue Sun,et al. Learning Optimal Controllers by Policy Gradient: Global Optimality via Convex Parameterization , 2021, 2021 60th IEEE Conference on Decision and Control (CDC).
[14] Laura Balzano,et al. Identification and Adaptive Control of Markov Jump Systems: Sample Complexity and Regret Bounds , 2021, ArXiv.
[15] Max Simchowitz,et al. Stabilizing Dynamical Systems via Policy Gradient Methods , 2021, NeurIPS.
[16] J. Slotine,et al. Contraction Theory for Nonlinear Stability Analysis and Learning-based Control: A Tutorial Overview , 2021, Annu. Rev. Control..
[17] Alexandre Proutiere,et al. Minimal Expected Regret in Linear Quadratic Control , 2021, AISTATS.
[18] Prateek Jain,et al. Near-optimal Offline and Streaming Algorithms for Learning Non-Linear Dynamical Systems , 2021, NeurIPS.
[19] G. Ferrari-Trecate,et al. Near-Optimal Design of Safe Output-Feedback Controllers From Noisy Data , 2021, IEEE Transactions on Automatic Control.
[20] George J. Pappas,et al. Linear Systems can be Hard to Learn , 2021, 2021 60th IEEE Conference on Decision and Control (CDC).
[21] Stephen Tu,et al. On the Sample Complexity of Stability Constrained Imitation Learning , 2021, L4DC.
[22] Max Simchowitz,et al. Task-Optimal Exploration in Linear Dynamical Systems , 2021, ICML.
[23] B. Hambly,et al. Policy Gradient Methods for the Noisy Linear Quadratic Regulator over a Finite Horizon , 2020, SIAM J. Control. Optim..
[24] Holden Lee. Improved rates for prediction and identification of partially observed linear dynamical systems , 2020, ALT.
[25] Stuart J. Russell,et al. SLIP: Learning to Predict in Unknown Dynamical Systems with Long-Term Memory , 2020, NeurIPS.
[26] Salar Fattahi,et al. Learning Partially Observed Linear Dynamical Systems from Logarithmic Number of Samples , 2020, L4DC.
[27] O. Papaspiliopoulos. High-Dimensional Probability: An Introduction with Applications in Data Science , 2020 .
[28] Na Li,et al. Non-Asymptotic Identification of Linear Dynamical Systems Using Multiple Trajectories , 2020, IEEE Control Systems Letters.
[29] Alessandro Lazaric,et al. Efficient Optimistic Exploration in Linear-Quadratic Regulators via Lagrangian Relaxation , 2020, ICML.
[30] Michael I. Jordan,et al. Active Learning for Nonlinear System Identification with Guarantees , 2020, J. Mach. Learn. Res..
[31] Xian Wu,et al. Least Squares Regression with Markovian Data: Fundamental Limits and Algorithms , 2020, NeurIPS.
[32] G. A. Young,et al. High‐dimensional Statistics: A Non‐asymptotic Viewpoint, Martin J.Wainwright, Cambridge University Press, 2019, xvii 552 pages, £57.99, hardback ISBN: 978‐1‐1084‐9802‐9 , 2020, International Statistical Review.
[33] Dylan J. Foster,et al. Learning nonlinear dynamical systems from a single trajectory , 2020, L4DC.
[34] Babak Hassibi,et al. Logarithmic Regret Bound in Partially Observable Linear Dynamical Systems , 2020, NeurIPS.
[35] Alexandre Proutiere,et al. Finite-time Identification of Stable Linear Systems Optimality of the Least-Squares Estimator , 2020, 2020 59th IEEE Conference on Decision and Control (CDC).
[36] B. Hassibi,et al. Adaptive Control and Regret Minimization in Linear Quadratic Gaussian (LQG) Setting , 2020, 2021 American Control Conference (ACC).
[37] Samet Oymak,et al. Non-asymptotic and Accurate Learning of Nonlinear Dynamical Systems , 2020, J. Mach. Learn. Res..
[38] Alon Cohen,et al. Logarithmic Regret for Learning Linear Quadratic Regulators Efficiently , 2020, ICML.
[39] George J. Pappas,et al. Online Learning of the Kalman Filter With Logarithmic Regret , 2020, IEEE Transactions on Automatic Control.
[40] Kevin G. Jamieson,et al. Active Learning for Identification of Linear Dynamical Systems , 2020, COLT.
[41] Karan Singh,et al. No-Regret Prediction in Marginally Stable Systems , 2020, COLT.
[42] Max Simchowitz,et al. Naive Exploration is Optimal for Online LQR , 2020, ICML.
[43] Max Simchowitz,et al. Improper Learning for Non-Stochastic Control , 2020, COLT.
[44] Jaouad Mourtada. Exact minimax risk for linear least squares, and the lower tail of sample covariance matrices , 2019, The Annals of Statistics.
[45] C. Rojas,et al. Finite impulse response models: A non-asymptotic analysis of the least squares estimator , 2019, Bernoulli.
[46] Wojciech M. Czarnecki,et al. Grandmaster level in StarCraft II using multi-agent reinforcement learning , 2019, Nature.
[47] Bruce Lee,et al. Non-asymptotic Closed-Loop System Identification using Autoregressive Processes and Hankel Model Reduction , 2019, 2020 59th IEEE Conference on Decision and Control (CDC).
[48] Nikolai Matni,et al. A Tutorial on Concentration Bounds for System Identification , 2019, 2019 IEEE 58th Conference on Decision and Control (CDC).
[49] Yishay Mansour,et al. Learning Linear-Quadratic Regulators Efficiently with only $\sqrt{T}$ Regret , 2019, ICML.
[50] Nikolai Matni,et al. Learning Sparse Dynamical Systems from a Single Sample Trajectory , 2019, 2019 IEEE 58th Conference on Decision and Control (CDC).
[51] Alexandre Proutière,et al. Sample Complexity Lower Bounds for Linear System Identification , 2019, 2019 IEEE 58th Conference on Decision and Control (CDC).
[52] George J. Pappas,et al. Finite Sample Analysis of Stochastic System Identification , 2019, 2019 IEEE 58th Conference on Decision and Control (CDC).
[53] Benjamin Recht,et al. Certainty Equivalence is Efficient for Linear Quadratic Control , 2019, NeurIPS.
[54] Max Simchowitz,et al. Learning Linear Dynamical Systems with Semi-Parametric Least Squares , 2019, COLT.
[55] Alexander Rakhlin,et al. Near optimal finite time identification of arbitrary linear dynamical systems , 2018, ICML.
[56] Benjamin Recht,et al. The Gap Between Model-Based and Model-Free Methods on the Linear Quadratic Regulator: An Asymptotic Viewpoint , 2018, COLT.
[57] Ambuj Tewari,et al. Input perturbations for adaptive control and learning , 2018, Autom..
[58] Nikolai Matni,et al. Safely Learning to Control the Constrained Linear Quadratic Regulator , 2018, 2019 American Control Conference (ACC).
[59] Shie Mannor,et al. On-Line Learning of Linear Dynamical Systems: Exponential Forgetting in Kalman Filters , 2018, AAAI.
[60] Alessandro Lazaric,et al. Improved Regret Bounds for Thompson Sampling in Linear Quadratic Control Problems , 2018, ICML.
[61] Nikolai Matni,et al. Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator , 2018, NeurIPS.
[62] Nikolai Matni,et al. Finite-Data Performance Guarantees for the Output-Feedback Control of an Unknown System , 2018, 2018 IEEE Conference on Decision and Control (CDC).
[63] Michael I. Jordan,et al. Learning Without Mixing: Towards A Sharp Analysis of Linear System Identification , 2018, COLT.
[64] Sham M. Kakade,et al. Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator , 2018, ICML.
[65] Ambuj Tewari,et al. Finite Time Identification in Unstable Linear Systems , 2017, Autom..
[66] Nikolai Matni,et al. On the Sample Complexity of the Linear Quadratic Regulator , 2017, Foundations of Computational Mathematics.
[67] Yi Ouyang,et al. Learning-based Control of Unknown Linear Systems with Thompson Sampling , 2017, ArXiv.
[68] Benjamin Recht,et al. Non-Asymptotic Analysis of Robust Control from Coarse-Grained Identification , 2017, ArXiv.
[69] Tengyu Ma,et al. Gradient Descent Learns Linear Dynamical Systems , 2016, J. Mach. Learn. Res..
[70] Mark W. Schmidt,et al. Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Łojasiewicz Condition , 2016, ECML/PKDD.
[71] Demis Hassabis,et al. Mastering the game of Go with deep neural networks and tree search , 2016, Nature.
[72] S. Mendelson,et al. Regularization and the small-ball method I: sparse recovery , 2016, 1601.05584.
[73] Shie Mannor,et al. Online Learning for Adversaries with Memory: Price of Past Mistakes , 2015, NIPS.
[74] Yuval Tassa,et al. Continuous control with deep reinforcement learning , 2015, ICLR.
[75] Max Simchowitz,et al. Low-rank Solutions of Linear Matrix Equations via Procrustes Flow , 2015, ICML.
[76] S. Mendelson. Learning without concentration for general loss functions , 2014, 1410.3192.
[77] Harshad Deshmane,et al. System Identification via Nuclear Norm Regularization , 2014 .
[78] Shahar Mendelson,et al. Learning without Concentration , 2014, COLT.
[79] Roberto Imbuzeiro Oliveira,et al. The lower tail of random quadratic forms with applications to ordinary least squares , 2013, ArXiv.
[80] S. Boucheron,et al. Concentration Inequalities: A Nonasymptotic Theory of Independence , 2013 .
[81] Csaba Szepesvári,et al. Regret Bounds for the Adaptive Control of Linear Quadratic Systems , 2011, COLT.
[82] Csaba Szepesvári,et al. Improved Algorithms for Linear Stochastic Bandits , 2011, NIPS.
[83] Bart De Moor,et al. Subspace Identification for Linear Systems: Theory ― Implementation ― Applications , 2011 .
[84] Martin J. Wainwright,et al. A unified framework for high-dimensional analysis of $M$-estimators with decomposable regularizers , 2009, NIPS.
[85] Mathukumalli Vidyasagar,et al. A learning theory approach to system identification and stochastic adaptive control , 2008 .
[86] P. Bickel,et al. SIMULTANEOUS ANALYSIS OF LASSO AND DANTZIG SELECTOR , 2008, 0801.1095.
[87] V. Verdult,et al. Filtering and System Identification: A Least Squares Approach , 2007 .
[88] Si-Zhao Joe Qin,et al. An overview of subspace identification , 2006, Comput. Chem. Eng..
[89] Dietmar Bauer,et al. Comparing the CCA Subspace Method to Pseudo Maximum Likelihood Methods in the case of No Exogenous Inputs , 2005 .
[90] Dietmar Bauer,et al. Asymptotic properties of subspace estimators , 2005, Autom..
[91] M. Wagner,et al. Estimating cointegrated systems using subspace algorithms , 2002 .
[92] A. Winter,et al. Strong converse for identification via quantum channels , 2000, IEEE Trans. Inf. Theory.
[93] M. Deistler,et al. On the Impact of Weighting Matrices in Subspace Algorithms , 2000 .
[94] M. Campi,et al. Finite sample properties of system identification methods , 1999, Proceedings of the 38th IEEE Conference on Decision and Control (Cat. No.99CH36304).
[95] Dietmar Bauer,et al. Consistency and asymptotic normality of some subspace algorithms for systems without observed inputs , 1999, Autom..
[96] Iven M. Y. Mareels,et al. Finite sample properties of linear model identification , 1999, IEEE Trans. Autom. Control..
[97] Alexander Goldenshluger,et al. Nonparametric Estimation of Transfer Functions: Rates of Convergence and Adaptation , 1998, IEEE Trans. Inf. Theory.
[98] R. Gill,et al. Applications of the van Trees inequality : a Bayesian Cramr-Rao bound , 1995 .
[99] Petros G. Voulgaris,et al. On optimal ℓ∞ to ℓ∞ filtering , 1995, Autom..
[100] Lennart Ljung,et al. Performance analysis of general tracking algorithms , 1994, Proceedings of 1994 33rd IEEE Conference on Decision and Control.
[101] Manfred Deistler,et al. Consistency and relative efficiency of subspace methods , 1994, Autom..
[102] K. Poolla,et al. On the time complexity of worst-case system identification , 1994, IEEE Trans. Autom. Control..
[103] J. Tsitsiklis,et al. The sample complexity of worst-case identification of FIR linear systems , 1993, Proceedings of 32nd IEEE Conference on Decision and Control.
[104] L. Ljung,et al. Asymptotic properties of the least-squares method for estimating transfer functions and disturbance spectra , 1992, Advances in Applied Probability.
[105] E. Hannan,et al. The statistical theory of linear systems , 1989 .
[106] Jan Willem Polderman,et al. On the necessity of identifying the true parameter in adaptive LQ control , 1986 .
[107] Lennart Ljung,et al. Optimal experiment designs with respect to the intended model application , 1986, Autom..
[108] T. Lai. Asymptotically efficient adaptive control in stochastic regression models , 1986 .
[109] E. Bai,et al. Persistency of excitation, sufficient richness and parameter convergence in discrete time adaptive control☆ , 1985 .
[110] Woei Lin,et al. Will the self-tuning approach work for general cost criteria? , 1985 .
[111] T. Lai,et al. Asymptotic properties of general autoregressive models and strong consistency of least-squares estimates of their parameters , 1983 .
[112] Dante C. Youla,et al. Modern Wiener-Hopf Design of Optimal Controllers. Part I , 1976 .
[113] M. Hestenes. Quadratic control problems , 1975 .
[114] P. Wedin. Perturbation bounds in connection with singular value decomposition , 1972 .
[115] A. A. Feldbaum,et al. DUAL CONTROL THEORY, IV , 1961 .
[116] A. Wald,et al. On the Statistical Treatment of Linear Stochastic Difference Equations , 1943 .
[117] H. Hjalmarsson,et al. Regret Minimization for Linear Quadratic Adaptive Controllers Using Fisher Feedback Exploration , 2022, IEEE Control Systems Letters.
[118] Munther A. Dahleh,et al. Finite Time LTI System Identification , 2021, J. Mach. Learn. Res..
[119] Prof. Dr. Pavol Quittner,et al. Systems , 2019, Superlinear Parabolic Problems.
[120] Erik Weyer,et al. Finite-Sample System Identification: An Overview and a New Correlation Method , 2018, IEEE Control Systems Letters.
[121] Javier García,et al. A comprehensive survey on safe reinforcement learning , 2015, J. Mach. Learn. Res..
[122] Mihailo R. Jovanović,et al. System Identification via Nuclear Norm Regularization , 2014 .
[123] M. Gevers. Identification for Control: From the Early Achievements to the Revival of Experiment Design , 2005, Proceedings of the 44th IEEE Conference on Decision and Control.
[124] A. Chiuso,et al. The asymptotic variance of subspace estimates , 2004 .
[125] Tamal Mukherjee,et al. System-Level Synthesis , 2003 .
[126] T. Lai,et al. Asymptotic Properties of General Autoregressive Models and Strong Consistency of Least-Squares Estimates of Their Parameters , 2003 .
[127] Tamer Basar,et al. Dual Control Theory , 2001 .
[128] T. Başar. Feedback and Optimal Sensitivity: Model Reference Transformations, Multiplicative Seminorms, and Approximate Inverses , 2001 .
[129] T. Söderström. Discrete-Time Stochastic Systems: Estimation and Control , 1995 .
[130] Petko Hr. Petkov,et al. Perturbation analysis of the discrete Riccati equation , 1993, Kybernetika.
[131] Lennart Ljung,et al. System Identification: Theory for the User , 1987 .
[132] B. Mark. On Self Tuning Regulators , 1972 .
[133] H. Simon,et al. Dynamic Programming Under Uncertainty with a Quadratic Criterion Function , 1956 .