The reviewed record of science sign in
Pith

arxiv: 2606.12691 · v1 · pith:OAQGB7OG · submitted 2026-06-10 · cs.LG · cs.AI· cs.SY· eess.SY· math.OC· stat.ML

Two-Layer Linear Auto-Regressive Models Estimate Latent States

Yahya Sattar , Sunmook Choi , Leo Maynard-Zhang , Yassir Jedra , Maryam Fazel , Sarah Dean This is my paper

Reviewed by Pith2026-06-27 09:56 UTCgrok-4.3pith:OAQGB7OGopen to challenge →

classification cs.LG cs.AIcs.SYeess.SYmath.OCstat.ML
keywords auto-regressive modelsKalman filterlatent state estimationlinear dynamical systemsempirical risk minimizationstate recoverypartially observed systems
0
0 comments X

The pith

Two-layer linear auto-regressive models recover Kalman filter state estimates when trained by empirical risk minimization on data from partially observed linear dynamical systems.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This paper establishes that two-layer linear auto-regressive models, when trained by empirical risk minimization on sequences from partially observed linear dynamical systems, learn hidden representations that coincide up to similarity transformation with the state estimates of the optimal Kalman filter. The models achieve this without explicit knowledge of the underlying dynamics or states. The result rests on three elements: the Kalman filter admits an auto-regressive approximation with bounded truncation error, the non-convex training landscape is benign with only global minima and strict saddles as stationary points, and finite-sample bounds control prediction error, parameter error, and state recovery error. A sympathetic reader would care because the finding supplies a concrete mechanism by which simple auto-regressive architectures implicitly perform classical optimal filtering on linear systems.

Core claim

When trained by empirical risk minimization on data from partially observed linear dynamical systems, two-layer linear auto-regressive models naturally learn to approximate Kalman filtering. In particular, the learned hidden representation coincides, up to a similarity transformation, with the state estimates produced by the optimal Kalman filter, even though the model has no explicit knowledge of the underlying dynamics or state. The result follows from establishing that the Kalman filter is well approximated by an auto-regressive model with bounded truncation error, that the two-layer optimization landscape is benign despite non-convexity, and that finite-sample guarantees hold for predict

What carries the argument

The two-layer linear auto-regressive model whose hidden layer is trained by empirical risk minimization to produce next-step predictions, thereby recovering latent states as a byproduct.

If this is right

  • Finite-sample guarantees hold simultaneously for prediction error, parameter estimation error, and latent state recovery.
  • The Kalman filter itself admits a bounded-error auto-regressive approximation.
  • All stationary points of the two-layer training problem are either strict saddles or global minima.
  • Numerical simulations confirm that the learned latent representations recover the Kalman state estimates.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same benign-landscape argument may apply to deeper linear or mildly nonlinear auto-regressive architectures, suggesting a route to implicit filtering in higher-order systems.
  • Auto-regressive training could serve as a model-free alternative to explicit Kalman-filter design whenever the system is approximately linear.
  • The result raises the question of whether similar recovery guarantees exist for other classical estimators, such as particle filters, when the observation model is replaced by a learned auto-regressive layer.

Load-bearing premise

The two-layer non-convex optimization landscape is benign, with every stationary point being either a strict saddle or a global minimum.

What would settle it

A concrete counter-example in which a two-layer linear auto-regressive model trained to a stationary point on data from a partially observed linear dynamical system yields hidden representations that do not match Kalman filter state estimates up to any similarity transformation.

Figures

Figures reproduced from arXiv: 2606.12691 by Leo Maynard-Zhang, Maryam Fazel, Sarah Dean, Sunmook Choi, Yahya Sattar, Yassir Jedra.

Figure 1
Figure 1. Figure 1: Two-layer auto-regressive model architecture [PITH_FULL_IMAGE:figures/full_fig_p004_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Alignment between the predicted state estimates and learned activations. We plot the first [PITH_FULL_IMAGE:figures/full_fig_p011_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Sample complexity of latent state recovery. Average [PITH_FULL_IMAGE:figures/full_fig_p012_3.png] view at source ↗
read the original abstract

Auto-regressive models have emerged as powerful tools for sequential data, from language to video. Understanding how and why these models learn latent representations remains an open theoretical question. In this work, we demonstrate that when trained by empirical risk minimization on data from partially observed linear dynamical systems, two-layer linear auto-regressive models naturally learn to approximate Kalman filtering. In particular, we show that the learned hidden representation coincides, up to a similarity transformation, with the state estimates produced by the optimal (Kalman) filter, even though the model has no explicit knowledge of the underlying dynamics or state. The result follows from three main insights. First, we establish that the Kalman filter is well approximated by an auto-regressive model with bounded truncation error. Second, we show that despite non-convexity, the two-layer optimization landscape is benign, i.e., all stationary points are either strict saddles or global minima. Finally, as our main contributions, we provide finite-sample guarantees on prediction error, parameter estimation error, and latent state recovery. Numerical simulations support the theoretical results and demonstrate that the latent representations of auto-regressive models recover state estimates.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 3 minor

Summary. The paper claims that two-layer linear auto-regressive models trained by empirical risk minimization on data from partially observed linear dynamical systems learn hidden representations that coincide, up to similarity transformation, with the state estimates of the optimal Kalman filter. This follows from three insights: (i) the Kalman filter is well-approximated by an AR model with bounded truncation error, (ii) the non-convex two-layer optimization landscape is benign (all stationary points are strict saddles or global minima), and (iii) finite-sample guarantees on prediction error, parameter estimation error, and latent-state recovery. Numerical simulations are provided in support.

Significance. If correct, the result supplies a theoretical account of how simple AR models can recover latent states in sequential data without explicit dynamics knowledge, linking AR prediction to Kalman filtering. The finite-sample guarantees on latent-state recovery constitute a concrete strength. The benign-landscape property is presented as one of the three main insights but is the least secure link for the central claim.

major comments (2)
  1. [§4, Theorem 4.1] §4 (Landscape Analysis), Theorem 4.1: the claim that all stationary points are strict saddles or global minima is load-bearing for the ERM-to-Kalman-recovery argument, yet the provided analysis does not explicitly rule out non-strict stationary points whose hidden-layer span fails to cover the observable subspace of the underlying LDS; such points would invalidate the subsequent latent-state recovery guarantee even if the global minimum is Kalman-like.
  2. [§3.1, Eq. (8)] §3.1 (Approximation), Eq. (8): the truncation-error bound for the AR approximation to the Kalman filter is stated to be independent of horizon, but the derivation appears to rely on the stability of the LDS; it is unclear whether the same bound holds uniformly when the process noise or observation noise covariance matrices are only partially known, which is the regime in which the finite-sample results are applied.
minor comments (3)
  1. [§2] Notation for the hidden representation h_t is introduced without an explicit statement of its dimension relative to the true state dimension; a short clarifying sentence would help readers track the similarity transformation.
  2. [Figure 2] Figure 2 caption does not indicate whether the plotted trajectories are single runs or averages over multiple random seeds; adding error bars or stating the number of trials would improve clarity of the empirical support.
  3. [Theorem 5.3] The finite-sample bound in Theorem 5.3 is stated in terms of the sample size n, but the dependence on the LDS parameters (e.g., the spectral radius) is only implicit; making the dependence explicit would aid comparison with related LDS identification results.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the careful and constructive review. We address each major comment below, indicating planned revisions where appropriate.

read point-by-point responses

  1. Referee: [§4, Theorem 4.1] §4 (Landscape Analysis), Theorem 4.1: the claim that all stationary points are strict saddles or global minima is load-bearing for the ERM-to-Kalman-recovery argument, yet the provided analysis does not explicitly rule out non-strict stationary points whose hidden-layer span fails to cover the observable subspace of the underlying LDS; such points would invalidate the subsequent latent-state recovery guarantee even if the global minimum is Kalman-like.

    Authors: We appreciate the referee highlighting the need for explicitness on this point. The proof of Theorem 4.1 proceeds by showing that any stationary point of the two-layer objective must align with the observable subspace of the LDS (otherwise a descent direction exists in the hidden-layer weights, violating stationarity). However, to make this argument fully explicit and rule out degenerate non-strict stationary points, we will add a supporting lemma in the revision that directly connects the stationarity condition to full span of the observable subspace. This will strengthen the link to the latent-state recovery result without altering the theorem statement. revision: yes

  2. Referee: [§3.1, Eq. (8)] §3.1 (Approximation), Eq. (8): the truncation-error bound for the AR approximation to the Kalman filter is stated to be independent of horizon, but the derivation appears to rely on the stability of the LDS; it is unclear whether the same bound holds uniformly when the process noise or observation noise covariance matrices are only partially known, which is the regime in which the finite-sample results are applied.

    Authors: The bound in Eq. (8) follows from the geometric series summation enabled by stability of the state-transition matrix (spectral radius strictly less than one), which is an assumption stated in Section 3 and used throughout the finite-sample analysis. The derivation depends on the system matrices and Kalman gain but holds for any fixed positive-definite noise covariances; it does not require the covariances to be known, only that they are bounded (which is implicit in the fixed but unknown LDS setting). The finite-sample results treat the entire LDS, including covariances, as fixed unknowns. We will insert a short remark after Eq. (8) clarifying uniformity over bounded covariances under the stability assumption. revision: partial

Circularity Check

0 steps flagged

No significant circularity; derivation self-contained

full rationale

The paper establishes the Kalman approximation by AR models, the benign landscape property, and finite-sample guarantees as separate insights derived from properties of linear dynamical systems and empirical risk minimization. The central claim that the learned hidden representation coincides with Kalman estimates follows from these without any reduction by construction to fitted parameters, self-definitional equations, or load-bearing self-citations. No patterns matching the enumerated circularity kinds are exhibited in the abstract or described contributions.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 0 invented entities

The central claim rests on domain assumptions about the data-generating process being a partially observed linear dynamical system and the optimization landscape being benign; no free parameters or invented entities are introduced in the abstract.

axioms (2)
  • domain assumption The underlying process is a partially observed linear dynamical system.
    The setting in which the result is claimed to hold, as stated in the abstract.
  • domain assumption The two-layer linear auto-regressive model has a benign optimization landscape where all stationary points are strict saddles or global minima.
    One of the three main insights required for the training to reach the approximating solution.

pith-pipeline@v0.9.1-grok · 5762 in / 1413 out tokens · 33838 ms · 2026-06-27T09:56:43.066079+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

49 extracted references · 3 canonical work pages

  1. [1]

    Optimal filtering

    Brian DO Anderson and John B Moore. Optimal filtering . Courier Corporation, 2005

    2005

  2. [2]

    Behavioral feedback for optimal lqg control

    Abed AlRahman Al Makdah, Vishaal Krishnan, Vaibhav Katewa, and Fabio Pasqualetti. Behavioral feedback for optimal lqg control. In 2022 IEEE 61st Conference on Decision and Control (CDC) , pages 4660--4666. IEEE, 2022

    2022

  3. [3]

    A new approach to learning linear dynamical systems

    Ainesh Bakshi, Allen Liu, Ankur Moitra, and Morris Yau. A new approach to learning linear dynamical systems. In Proceedings of the 55th Annual ACM Symposium on Theory of Computing , pages 335--348, 2023

    2023

  4. [4]

    Word2vec

    Kenneth Ward Church. Word2vec. Natural Language Engineering , 23(1):155--162, 2017

    2017

  5. [5]

    Universal learning of nonlinear dynamics

    Evan Dogariu, Anand Brahmbhatt, and Elad Hazan. Universal learning of nonlinear dynamics. arXiv preprint arXiv:2508.11990 , 2025

    work page arXiv 2025

  6. [6]

    Can transformers learn optimal filtering for unknown systems? IEEE Control Systems Letters , 7:3525--3530, 2023

    Zhe Du, Haldun Balim, Samet Oymak, and Necmiye Ozay. Can transformers learn optimal filtering for unknown systems? IEEE Control Systems Letters , 7:3525--3530, 2023

    2023

  7. [7]

    On the sample complexity of the linear quadratic regulator

    Sarah Dean, Horia Mania, Nikolai Matni, Benjamin Recht, and Stephen Tu. On the sample complexity of the linear quadratic regulator. FOCM , pages 1--47, 2019

    2019

  8. [8]

    On the gradient domination of the lqg problem

    Kasra Fallah, Leonardo F Toso, and James Anderson. On the gradient domination of the lqg problem. arXiv preprint arXiv:2507.09026 , 2025

    work page arXiv 2025

  9. [9]

    Netflix update: Try this at home, 2006

    Simon Funk. Netflix update: Try this at home, 2006

    2006

  10. [10]

    Imitation and transfer learning for lqg control

    Taosha Guo, Abed AlRahman Al Makdah, Vishaal Krishnan, and Fabio Pasqualetti. Imitation and transfer learning for lqg control. IEEE Control Systems Letters , 7:2149--2154, 2023

    2023

  11. [11]

    Can a transformer represent a kalman filter? In 6th Annual Learning for Dynamics & Control Conference , pages 1502--1512

    Gautam Goel and Peter Bartlett. Can a transformer represent a kalman filter? In 6th Annual Learning for Dynamics & Control Conference , pages 1502--1512. PMLR, 2024

    2024

  12. [12]

    Escaping from saddle points—online stochastic gradient for tensor decomposition

    Rong Ge, Furong Huang, Chi Jin, and Yang Yuan. Escaping from saddle points—online stochastic gradient for tensor decomposition. In Conference on learning theory , pages 797--842. PMLR, 2015

    2015

  13. [13]

    No-regret prediction in marginally stable systems

    Udaya Ghai, Holden Lee, Karan Singh, Cyril Zhang, and Yi Zhang. No-regret prediction in marginally stable systems. In Conference on Learning Theory , pages 1714--1757. PMLR, 2020

    2020

  14. [14]

    Effective construction of linear state-variable models from input/output functions

    BL Ho and Rudolf E K \'a lm \'a n. Effective construction of linear state-variable models from input/output functions. at-Automatisierungstechnik , 14(1-12):545--548, 1966

    1966

  15. [15]

    A tail inequality for quadratic forms of subgaussian random vectors

    Daniel Hsu, Sham Kakade, Tong Zhang, et al. A tail inequality for quadratic forms of subgaussian random vectors. Electronic Communications in Probability , 17, 2012

    2012

  16. [16]

    Gradient descent learns linear dynamical systems

    Moritz Hardt, Tengyu Ma, and Benjamin Recht. Gradient descent learns linear dynamical systems. The Journal of Machine Learning Research , 19(1):1025--1068, 2018

    2018

  17. [17]

    The Elements of Statistical Learning: Data Mining, Inference, and Prediction

    Trevor Hastie, Robert Tibshirani, and Jerome Friedman. The Elements of Statistical Learning: Data Mining, Inference, and Prediction . Springer Science & Business Media, New York, NY, 2nd edition, 2009

    2009

  18. [18]

    How to escape saddle points efficiently

    Chi Jin, Rong Ge, Praneeth Netrapalli, Sham M Kakade, and Michael I Jordan. How to escape saddle points efficiently. In International conference on machine learning , pages 1724--1732. PMLR, 2017

    2017

  19. [19]

    Matrix factorization techniques for recommender systems

    Yehuda Koren, Robert Bell, and Chris Volinsky. Matrix factorization techniques for recommender systems. Computer , 42(8):30--37, 2009

    2009

  20. [20]

    Consistency analysis of subspace identification methods based on a linear regression approach

    Torben Knudsen. Consistency analysis of subspace identification methods based on a linear regression approach. Automatica , 37(1):81--89, 2001

    2001

  21. [21]

    Iterative matrix bounds and computational solutions to the discrete algebraic riccati equation

    N Komaroff. Iterative matrix bounds and computational solutions to the discrete algebraic riccati equation. IEEE Transactions on Automatic Control , 39(8):1676--1678, 2002

    2002

  22. [22]

    Logarithmic regret bound in partially observable linear dynamical systems

    Sahin Lale, Kamyar Azizzadenesheli, Babak Hassibi, and Anima Anandkumar. Logarithmic regret bound in partially observable linear dynamical systems. Advances in Neural Information Processing Systems , 33:20876--20888, 2020

    2020

  23. [23]

    Emergent world representations: Exploring a sequence model trained on a synthetic task

    Kenneth Li, Aspen K Hopkins, David Bau, Fernanda B Vi \'e gas, Hanspeter Pfister, and Martin Wattenberg. Emergent world representations: Exploring a sequence model trained on a synthetic task. In The Eleventh International Conference on Learning Representations , 2023

    2023

  24. [24]

    Non-asymptotic closed-loop system identification using autoregressive processes and hankel model reduction

    Bruce Lee and Andrew Lamperski. Non-asymptotic closed-loop system identification using autoregressive processes and hankel model reduction. In 2020 59th IEEE Conference on Decision and Control (CDC) , pages 3419--3424. IEEE, 2020

    2020

  25. [25]

    Gradient descent only converges to minimizers

    Jason D Lee, Max Simchowitz, Michael I Jordan, and Benjamin Recht. Gradient descent only converges to minimizers. In Conference on learning theory , pages 1246--1257. PMLR, 2016

    2016

  26. [26]

    Non-asymptotic identification of lti systems from a single trajectory

    Samet Oymak and Necmiye Ozay. Non-asymptotic identification of lti systems from a single trajectory. American Control Conference , 2019

    2019

  27. [27]

    Revisiting ho--kalman-based system identification: Robustness and finite-sample analysis

    Samet Oymak and Necmiye Ozay. Revisiting ho--kalman-based system identification: Robustness and finite-sample analysis. IEEE Transactions on Automatic Control , 67(4):1914--1928, 2021

    1914

  28. [28]

    Guaranteed minimum-rank solutions of linear matrix equations via nuclear norm minimization

    Benjamin Recht, Maryam Fazel, and Pablo A Parrilo. Guaranteed minimum-rank solutions of linear matrix equations via nuclear norm minimization. SIAM review , 52(3):471--501, 2010

    2010

  29. [29]

    Learning linear dynamical systems with semi-parametric least squares

    Max Simchowitz, Ross Boczar, and Benjamin Recht. Learning linear dynamical systems with semi-parametric least squares. In Conference on Learning Theory , pages 2714--2802. PMLR, 2019

    2019

  30. [30]

    Learning without mixing: Towards a sharp analysis of linear system identification

    Max Simchowitz, Horia Mania, Stephen Tu, Michael I Jordan, and Benjamin Recht. Learning without mixing: Towards a sharp analysis of linear system identification. In Conference On Learning Theory , pages 439--473. PMLR, 2018

    2018

  31. [31]

    Finite sample identification of low-order lti systems via nuclear norm regularization

    Yue Sun, Samet Oymak, and Maryam Fazel. Finite sample identification of low-order lti systems via nuclear norm regularization. IEEE Open Journal of Control Systems , 1:237--254, 2022

    2022

  32. [32]

    Finite time lti system identification

    Tuhin Sarkar, Alexander Rakhlin, and Munther A Dahleh. Finite time lti system identification. Journal of Machine Learning Research , 22(26):1--61, 2021

    2021

  33. [33]

    The data-based lqg control problem

    Robert E Skelton and Guojun Shi. The data-based lqg control problem. In Proceedings of 1994 33rd IEEE Conference on Decision and Control , volume 2, pages 1447--1452. IEEE, 1994

    1994

  34. [34]

    Low-rank solutions of linear matrix equations via procrustes flow

    Stephen Tu, Ross Boczar, Max Simchowitz, Mahdi Soltanolkotabi, and Ben Recht. Low-rank solutions of linear matrix equations via procrustes flow. In Proceedings of The 33rd International Conference on Machine Learning , volume 48 of Proceedings of Machine Learning Research , pages 964--973, New York, New York, USA, 20--22 Jun 2016. PMLR

    2016

  35. [35]

    Nonconvex linear system identification with minimal state representation

    Uday Kiran Reddy Tadipatri, Benjamin D Haeffele, Joshua Agterberg, Ingvar Ziemann, and Rene Vidal. Nonconvex linear system identification with minimal state representation. In 7th Annual Learning for Dynamics & Control Conference , pages 1286--1299. PMLR, 2025

    2025

  36. [36]

    Finite sample analysis of stochastic system identification

    Anastasios Tsiamis and George J Pappas. Finite sample analysis of stochastic system identification. In 2019 IEEE 58th Conference on Decision and Control (CDC) , pages 3648--3654. IEEE, 2019

    2019

  37. [37]

    Chess as a testbed for language model state tracking

    Shubham Toshniwal, Sam Wiseman, Karen Livescu, and Kevin Gimpel. Chess as a testbed for language model state tracking. In Proceedings of the AAAI Conference on Artificial Intelligence , volume 36, pages 11385--11393, 2022

    2022

  38. [38]

    Yi Tian, Kaiqing Zhang, Russ Tedrake, and Suvrit Sra. Can direct latent model learning solve linear quadratic gaussian control? In Proceedings of The 5th Annual Learning for Dynamics and Control Conference , volume 211 of Proceedings of Machine Learning Research , pages 51--63. PMLR, 15--16 Jun 2023

    2023

  39. [39]

    Toward understanding state representation learning in muzero: A case study in linear quadratic gaussian control

    Yi Tian, Kaiqing Zhang, Russ Tedrake, and Suvrit Sra. Toward understanding state representation learning in muzero: A case study in linear quadratic gaussian control. In 2023 62nd IEEE Conference on Decision and Control (CDC) , pages 6166--6171. IEEE, 2023

    2023

  40. [40]

    Globally convergent policy search over dynamic filters for output estimation

    Jack Umenberger, Max Simchowitz, Juan C Perdomo, Kaiqing Zhang, and Russ Tedrake. Globally convergent policy search over dynamic filters for output estimation. arXiv preprint arXiv:2202.11659 , 2022

    work page arXiv 2022

  41. [41]

    What has a foundation model found? using inductive bias to probe for world models

    Keyon Vafa, Peter G Chang, Ashesh Rambachan, and Sendhil Mullainathan. What has a foundation model found? using inductive bias to probe for world models. In International Conference on Machine Learning , pages 60727--60747. PMLR, 2025

    2025

  42. [42]

    Models for dynamics

    Jan C Willems. Models for dynamics. In Dynamics reported: a series in dynamical systems and their applications , pages 171--269. Springer, 1989

    1989

  43. [43]

    Data-driven policy gradient method for optimal output feedback control of lqr

    Jun Xie and Yuan-Hua Ni. Data-driven policy gradient method for optimal output feedback control of lqr. In 2024 14th Asian Control Conference (ASCC) , pages 1039--1044. IEEE, 2024

    2024

  44. [44]

    Globally convergent policy gradient methods for linear quadratic control of partially observed systems

    Feiran Zhao, Xingyun Fu, and Keyou You. Globally convergent policy gradient methods for linear quadratic control of partially observed systems. IFAC-PapersOnLine , 56(2):5506--5511, 2023

    2023

  45. [45]

    Controlgym: Large-scale control environments for benchmarking reinforcement learning algorithms

    Xiangyuan Zhang, Weichao Mao, Saviz Mowlavi, Mouhacine Benosman, and Tamer Ba s ar. Controlgym: Large-scale control environments for benchmarking reinforcement learning algorithms. In 6th Annual Learning for Dynamics & Control Conference , pages 181--196. PMLR, 2024

    2024

  46. [46]

    The global optimization geometry of shallow linear neural networks

    Zhihui Zhu, Daniel Soudry, Yonina C Eldar, and Michael B Wakin. The global optimization geometry of shallow linear neural networks. Journal of Mathematical Imaging and Vision , 62(3):279--292, 2020

    2020

  47. [47]

    Single trajectory nonparametric learning of nonlinear dynamics

    Ingvar M Ziemann, Henrik Sandberg, and Nikolai Matni. Single trajectory nonparametric learning of nonlinear dynamics. In Conference on Learning Theory , pages 3333--3364. PMLR, 2022

    2022

  48. [48]

    Learning with little mixing

    Ingvar Ziemann and Stephen Tu. Learning with little mixing. Advances in Neural Information Processing Systems , 35:4626--4637, 2022

    2022

  49. [49]

    A tutorial on the non-asymptotic theory of system identification

    Ingvar Ziemann, Anastasios Tsiamis, Bruce Lee, Yassir Jedra, Nikolai Matni, and George J Pappas. A tutorial on the non-asymptotic theory of system identification. In 2023 62nd IEEE Conference on Decision and Control (CDC) , pages 8921--8939. IEEE, 2023

    2023