reference.bib

@inproceedings{Ross2011_AISTATS,
  title={A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning},
  author={Ross, St{\'e}phane and Gordon, Geoffrey J and Bagnell, J.Andrew},
  booktitle={AISTATS},
  year={2011}
}

@inproceedings{ross2011_CVPR,
  title={Learning message-passing inference machines for structured prediction},
  author={Ross, Stephane and Munoz, Daniel and Hebert, Martial and Bagnell, J Andrew},
  booktitle={CVPR},
  pages={2737--2744},
  year={2011},
}

@article{Boots2011_IJRR,
  title={Closing the learning-planning loop with predictive state representations},
  author={Boots, Byron and Siddiqi, Sajid M and Gordon, Geoffrey J},
  journal={IJRR},
  volume={30},
  number={7},
  pages={954--966},
  year={2011},
  publisher={SAGE Publications}
}

@inproceedings{Zinkevich2003_ICML,
author = {Zinkevich, Martin},
booktitle = {ICML},
title = {{Online Convex Programming and Generalized Infinitesimal Gradient Ascent}},
year = {2003}
}

@article{Ahmed2015_Nips,
  title={A New View of Predictive State Methods for Dynamical System Learning},
  author={Hefny, Ahmed and Downey, Carlton and Gordon, Geoffrey},
  journal={arXiv preprint arXiv:1505.05310},
  year={2015}
}

@article{Ahmed2015_Nips_toputbackin,
    title = {On Predictive Belief Methods for Dynamical System Learning},
    author = {Hefny, Ahmed and Downey, Carlton and J. Gordon, Geoffrey},
    journal = {NIPS},
    year = {2015}
}

@article{Ralaivola2004,
author = {Ralaivola, Liva and D'Alche-Buc, Florence},
title = {{Dynamical modeling with kernels for nonlinear time series prediction}},
journal = {NIPS},
year = {2004}
}
@article{Wingate2006,
author = {Wingate, David and Singh, Satinder},
journal = {ICML},
pages = {1017--1024},
title = {{Kernel predictive linear Gaussian models for nonlinear stochastic dynamical systems}},
year = {2006}
}
    
@MISC {x_plane,
    author       = "Laminar Research",
    title        = "X-Plane",
    howpublished = "DVD",
    year         = "2015"
}

@book{kleiber2008,
  title={Applied econometrics with R},
  author={Kleiber, Christian and Zeileis, Achim},
  year={2008},
  publisher={Springer Science \& Business Media}
}
% textbook on instrumental variables
@book{bowden1990,
  title={Instrumental variables},
  author={Bowden, Roger J and Turkington, Darrell A},
  volume={8},
  year={1990},
  publisher={Cambridge University Press}
}
%% INSTRUMENTAL VARIABLE APPLICATION REFERENCES
@techreport{card1993,
  title={Using geographic variation in college proximity to estimate the return to schooling},
  author={Card, David},
  year={1993},
  institution={National Bureau of Economic Research}
}

@article{greenland2000,
  title={An introduction to instrumental variables for epidemiologists},
  author={Greenland, Sander},
  journal={International Journal of Epidemiology},
  volume={29},
  number={4},
  pages={722--729},
  year={2000},
  publisher={IEA}
}

@article{miguel2004,
  title={Economic shocks and civil conflict: An instrumental variables approach},
  author={Miguel, Edward and Satyanath, Shanker and Sergenti, Ernest},
  journal={Journal of Political Economy},
  volume={112},
  number={4},
  pages={725--753},
  year={2004},
  publisher={JSTOR}
}
@article{soderstrom2002,
  title={Instrumental variable methods for system identification},
  author={S{\"o}derstr{\"o}m, Torsten and Stoica, Petre},
  journal={Circuits, Systems and Signal Processing},
  volume={21},
  number={1},
  pages={1--9},
  year={2002},
  publisher={Springer}
}
@inproceedings{Boots11a,	
  Author = "Byron Boots and Geoffrey J. Gordon ",
  Booktitle = "NIPS",
  Title = "Predictive State Temporal Difference Learning",
  Year = {2011}
}

@INPROCEEDINGS{Littman01,
    author = {Michael L. Littman and Richard S. Sutton and Satinder Singh},
    title = {Predictive Representations of State},
    booktitle = {NIPS},
    year = {2001},
    pages = {1555--1561},
    publisher = {MIT Press}
}
@inproceedings{Singh2004_UAI,
 author = {Singh, Satinder and James, Michael R. and Rudary, Matthew R.},
 title = {Predictive State Representations: A New Theory for Modeling Dynamical Systems},
 booktitle = {UAI},
 year = {2004},
} 

@article{rao2008linear,
  title={Linear models and generalizations},
  author={Rao, C Radhakrishna and Toutenburg, Helge and Shalabh, Heuman C and Schomaker, M},
  journal={Least Squares and Alternatives (3rd edition) Springer, Berlin Heidelberg New York},
  year={2008}
}

Automatically generated by Mendeley Desktop 1.13.1
Any changes to this file will be lost if it is regenerated by Mendeley.

BibTeX export options can be customized via Options -> BibTeX in Mendeley Desktop

@book{Hardy_Book,
author = {Hardy, Godfrey H.},
publisher = {American Mathematical Society},
title = {{Divergent series}},
year = {2000}
}
@inproceedings{Boots2012_ICML,
author = {Boots, Byron and Gordon, Geoffrey},
booktitle = {ICML},
title = {{Two-manifold problems with applications to nolinear system identification}},
year = {2012}
}
@inproceedings{Hsu2009_COLT,
author = {Hsu, Daniel and {M. Kakade}, Sham and Zhang, Tong},
booktitle = {COLT},
title = {{A spectral algorithm for learning hidden markov models}},
year = {2009}
}
@inproceedings{Boots2011_AAAI,
author = {Boots, Byron and Gordon, Geoffrey},
booktitle = {AAAI},
title = {{An online spectral learning algorithm for partially observable nonlinear dynamical systems}},
year = {2011}
}

@misc{X-plane,
booktitle = {http://www.x-plane.com/desktop/home/},
title = {{X-Plane}},
url = {http://www.x-plane.com/desktop/home/}
}
@misc{DA42,
booktitle = {http://www.diamondaircraft.com/aircraft/da42/specs\_da42\_ng.php},
title = {{Diamond Aircraft (DA42-NG)}},
url = {http://www.diamondaircraft.com/aircraft/da42/specs\_da42\_ng.php}
}

@phdthesis{Boots2012_Thesis,
author = {Boots, Byron},
school = {Carnegie Mellon University},
title = {{Spectral Approaches to Learning Predictive Representations}},
year = {2012}
}

@inproceedings{littlestone2014,
  title={From on-line to batch learning},
  author={Littlestone, Nick},
  booktitle={Proceedings of the second annual workshop on Computational learning theory},
  pages={269--284},
  year={2014}
}

@article{cesa2004,
  title={On the generalization ability of on-line learning algorithms},
  author={Cesa-Bianchi, Nicolo and Conconi, Alex and Gentile, Claudio},
  journal={Information Theory, IEEE Transactions on},
  volume={50},
  number={9},
  pages={2050--2057},
  year={2004},
  publisher={IEEE}
}

@book{cameron2005,
  title={Microeconometrics: methods and applications},
  author={Cameron, A Colin and Trivedi, Pravin K},
  year={2005},
  publisher={Cambridge university press}
}

@article{rao2008,
  title={Linear models and generalizations},
  author={Rao, C Radhakrishna and Toutenburg, Helge and Shalabh, Heuman C and Schomaker, M},
  journal={Least Squares and Alternatives (3rd edition) Springer, Berlin Heidelberg New York},
  year={2008}
}


@inproceedings{shalev2009mind,
  title={Mind the duality gap: Logarithmic regret algorithms for online optimization},
  author={Shalev-Shwartz, Shai and Kakade, Sham M},
  booktitle={NIPS},
  pages={1457--1464},
  year={2009}
}

@article{hazan2007logarithmic,
  title={Logarithmic regret algorithms for online convex optimization},
  author={Hazan, Elad and Agarwal, Amit and Kale, Satyen},
  journal={Machine Learning},
  volume={69},
  number={2-3},
  pages={169--192},
  year={2007},
}


@inproceedings{Ross2011,
  title={No-Regret Reductions for Imitation Learning and Structured Prediction},
  author={Ross, St{\'e}phane and Gordon, Geoffrey J and Bagnell, J. Andrew},
  booktitle={AISTATS},
  year={2011},
  organization={Citeseer}
}

@inproceedings{Ross2010,
  title={Efficient reductions for imitation learning},
  author={Ross, St{\'e}phane and Bagnell, J. Andrew},
  booktitle={AISTATS},
  pages={661--668},
  year={2010}
}

@article{Ross2011b,
  title={Stability conditions for online learnability},
  author={Ross, St{\'e}phane and Bagnell, J Andrew},
  journal={arXiv preprint arXiv:1108.3154},
  year={2011}
}

@article{Daume2009,
  title={Search-based structured prediction},
  author={Daum{\'e} III, Hal and Langford, John and Marcu, Daniel},
  journal={Machine learning},
  volume={75},
  number={3},
  pages={297--325},
  year={2009},
  publisher={Springer}
}

@article{Werbos1990,
  title={Backpropagation through time: what it does and how to do it},
  author={Werbos, Paul J},
  journal={Proceedings of the IEEE},
  volume={78},
  number={10},
  pages={1550--1560},
  year={1990},
  publisher={IEEE}
}

@inproceedings{Siddiqi07,
  author = "Siddiqi, Sajid and Boots, Byron and Gordon, Geoffrey J.",
  title = "A Constraint Generation Approach to Learning Stable Linear Dynamical Systems",
  booktitle = "NIPS 20 (NIPS-07)",
  year = "2007"
}

@inproceedings{Abbeel2005,
  title={Learning vehicular dynamics, with application to modeling helicopters},
  author={Abbeel, Pieter and Ganapathi, Varun and Ng, Andrew Y},
  booktitle={NIPS},
  pages={1--8},
  year={2005}
}

@inproceedings{Abbeel2005b,
  title={Learning first-order Markov models for control},
  author={Abbeel, Pieter and Ng, Andrew Y},
  booktitle={NIPS},
  pages={1--8},
  year={2005}
}

@inproceedings{Abbeel2005c,
  title={Exploration and apprenticeship learning in reinforcement learning},
  author={Abbeel, Pieter and Ng, Andrew Y},
  booktitle={ICML},
  pages={1--8},
  year={2005},
  organization={ACM}
}

@article{Bengio1994,
  title={Learning long-term dependencies with gradient descent is difficult},
  author={Bengio, Yoshua and Simard, Patrice and Frasconi, Paolo},
  journal={Neural Networks, IEEE Transactions on},
  volume={5},
  number={2},
  pages={157--166},
  year={1994},
  publisher={IEEE}
}

@inproceedings{Coates2008,
 author = {Coates, Adam and Abbeel, Pieter and Ng, Andrew Y.},
 title = {Learning for Control from Multiple Demonstrations},
 booktitle = {ICML},
 year = {2008},
 location = {Helsinki, Finland},
 pages = {144--151},
 address = {New York, NY, USA},
} 

@article{Sutton1998,
    year={1988},
    journal={Machine Learning},
    volume={3},
    title={Learning to predict by the methods of temporal differences},
    publisher={Kluwer Academic Publishers},
    author={Sutton, RichardS.},
    pages={9-44},
    language={English}
}

@article{Khansari2011,
  title={Learning stable nonlinear dynamical systems with gaussian mixture models},
  author={Khansari-Zadeh, Seyed Mohammad and Billard, Aude},
  journal={Robotics, IEEE Transactions on},
  volume={27},
  number={5},
  pages={943--957},
  year={2011},
  publisher={IEEE}
}

@inproceedings{Langford2009,
  title={Learning nonlinear dynamic models},
  author={Langford, John and Salakhutdinov, Ruslan and Zhang, Tong},
  booktitle={ICML},
  pages={593--600},
  year={2009},
  organization={ACM}
}

@inproceedings{Wang2005,
  title={Gaussian process dynamical models},
  author={Wang, Jack and Hertzmann, Aaron and Blei, David M},
  booktitle={NIPS},
  pages={1441--1448},
  year={2005}
}

%% ADDED FROM KDM KPCA REPORT
@article{Lazaro-Gredilla2010,
author = {L\'{a}zaro-Gredilla, M},
file = {:C$\backslash$:/Users/arunvenk/Dropbox/CMU/Research/LearningInverseRobots/Lit/Regression/lazaro-gredilla10a\_Sparse Spectrum Gaussian Process Regression.pdf:pdf},
journal = {The Journal of Machine Learning Research},
keywords = {computational efficiency,gaussian process,power spectrum,probabilistic regression,sparse approximation},
pages = {1865--1881},
title = {{Sparse spectrum Gaussian process regression}},
url = {http://dl.acm.org/citation.cfm?id=1859914},
volume = {11},
year = {2010}
}
@inproceedings{Rudary2005,
archivePrefix = {arXiv},
arxivId = {1207.1416},
author = {Rudary, Matthew and Singh, S and Wingate, David},
booktitle = {Conference on Uncertainty in Artificial Intelligence},
eprint = {1207.1416},
file = {:C$\backslash$:/Users/arunvenk/Dropbox/CMU/Research/LearningInverseRobots/Lit/SysID/Predictive Linear-Gaussian Models of Stochastic Dynamical Systems.pdf:pdf},
number = {21},
title = {{Predictive linear-Gaussian models of stochastic dynamical systems}},
url = {http://arxiv.org/abs/1207.1416},
year = {2005}
}
@article{Le2013,
author = {Le, Quoc and Sarl\'{o}s, Tamas and Smola, Alex},
file = {:C$\backslash$:/Users/arunvenk/Dropbox/CMU/Research/LearningInverseRobots/Lit/kernels/LeSarlosSmola\_ICML13.pdf:pdf},
journal = {ICML},
pages = {244--252},
title = {{Fastfood—Approximating Kernel Expansions in Loglinear Time}},
url = {http://ai.stanford.edu/~quocle/LeSarlosSmola\_ICML13\_supp.pdf},
year = {2013}
}

@article{ghahramani1999,
  title={Learning nonlinear dynamical systems using an EM algorithm},
  author={Ghahramani, Zoubin and Roweis, Sam T},
  journal={Advances in neural information processing systems},
  pages={431--437},
  year={1999},
  publisher={MIT; 1998}
}




@book{Scholkopf1998,
author = {Sch\"{o}lkopf, Bernhard and Burges, Christopher JC and Smola, Alexander J},
chapter = {20},
editor = {Sch\"{o}lkopf, Bernhard and Burges, Christopher J C and Smola, Alexander J.},
file = {:C$\backslash$:/Users/arunvenk/Dropbox/CMU/Research/LearningInverseRobots/Lit/kernels/scholkopf\_book\_Kernel Principal Component Analysis.pdf:pdf},
isbn = {0262194163},
publisher = {MIT Press},
title = {{Advances in Kernel Methods: Support Vector Learning}},
year = {1999}
}
@article{Ko2007,
author = {Ko, J and Klein, D J and Fox, D and Haehnel, D},
booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems},
doi = {10.1109/IROS.2007.4399284},
file = {:C$\backslash$:/Users/arunvenk/Dropbox/CMU/Research/LearningInverseRobots/Lit/other\_controls/gp-ukf-iros-07.pdf:pdf},
keywords = {Gaussian processes,Kalman filters,regression analy},
pages = {1901--1907},
title = {{GP-UKF: Unscented kalman filters with Gaussian process prediction and observation models}},
year = {2007}
}
@article{Mika1998,
author = {Mika, Sebastian and Sch\"{o}lkopf, B and Smola, AJ and M\"{u}ller, KR},
file = {:C$\backslash$:/Users/arunvenk/Dropbox/CMU/Research/LearningInverseRobots/Lit/kernels/Kernel PCA and De-Noising in Feature Spaces.pdf:pdf},
journal = {NIPS},
title = {{Kernel PCA and De-Noising in Feature Spaces.}},
url = {http://trac.assembla.com/mlea2\_cpa/export/9/doc/kpca-de-noising-feature-space.pdf},
year = {1998}
}
@article{Rahimi2008,
author = {Rahimi, Ali and Recht, Benjamin},
file = {:C$\backslash$:/Users/arunvenk/Dropbox/CMU/Research/LearningInverseRobots/Lit/08.nips\_Weighted Sums of Random Kitchen Sinks.pdf:pdf},
journal = {NIPS},
pages = {1--8},
title = {{Weighted sums of random kitchen sinks: Replacing minimization with randomization in learning}},
year = {2008}
}
@article{Ralaivola2004,
abstract = {We consider the question of predicting nonlinear time series. Kernel Dy- namical Modeling (KDM), a new method based on kernels, is proposed as an extension to linear dynamical models. The kernel trick is used twice: first, to learn the parameters of themodel, and second, to compute preimages of the time series predicted in the feature space by means of Support Vector Regression. Our model shows strong connection with the classicKalman Filtermodel, with the kernel feature space as hidden state space. KernelDynamicalModeling is tested against two benchmark time series and achieves high quality predictions.},
author = {Ralaivola, Liva and D'Alche-Buc, Florence},
file = {:C$\backslash$:/Users/arunvenk/Dropbox/CMU/Research/LearningInverseRobots/Lit/kernels/Dynamical Modeling with Kernels.pdf:pdf},
journal = {NIPS},
title = {{Dynamical modeling with kernels for nonlinear time series prediction}},
url = {http://books.google.com/books?hl=en\&lr=\&id=0F-9C7K8fQ8C\&oi=fnd\&pg=PA129\&dq=Dynamical+Modeling+with+Kernels+for+Nonlinear+Time+Series+Prediction\&ots=TGMrqVPa15\&sig=HVqIFqaOeO2jyA34H0wftHC0ICU},
year = {2004}
}
@article{Narendra1990,
author = {Narendra, Kumpati S and Parthasarathy, Kannan},
file = {:C$\backslash$:/Users/arunvenk/Dropbox/CMU/Research/LearningInverseRobots/Lit/SysID/learning/neural\_network\_sys\_id.pdf:pdf},
journal = {IEEE Transactions on Neural Networks},
pages = {4--27},
title = {{Identification and control of dynamical systems using neural networks}},
url = {http://ieeexplore.ieee.org/xpls/abs\_all.jsp?arnumber=80202},
year = {1990}
}
@article{Muller1997,
author = {M\"{u}ller, KR and Smola, AJ and R\"{a}tsch, G},
doi = {10.1007/BFb0020283},
file = {:C$\backslash$:/Users/arunvenk/Dropbox/CMU/Research/LearningInverseRobots/Lit/SysID/Predicting Time Series with SVM(SVR).pdf:pdf},
journal = {Artificial Neural Networks — ICANN'9},
pages = {999--1004},
title = {{Predicting time series with support vector machines}},
url = {http://link.springer.com/chapter/10.1007/BFb0020283},
volume = {1327},
year = {1997}
}
@article{Lefebvre2003,
address = {Coimbra, Portugal},
author = {Lefebvre, Tine and Bruyninckx, Herman and Schutter, Joris De},
booktitle = {Int. Conf. Advanced Robotics},
file = {:C$\backslash$:/Users/arunvenk/Dropbox/CMU/Research/LearningInverseRobots/Lit/other\_controls/non-minial\_state\_kalman\_filter\_param\_est.pdf:pdf},
pages = {136--141},
title = {{A non-minimal state Kalman filter for nonlinear parameter estimation applied to autonomous compliant motion}},
url = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.20.908\&rep=rep1\&type=pdf},
year = {2003}
}
@article{Wingate2006,
author = {Wingate, David and Singh, Satinder},
file = {:C$\backslash$:/Users/arunvenk/Dropbox/CMU/Research/LearningInverseRobots/Lit/kernels/wingate\_Kernel Predictive Linear Gaussian Models.pdf:pdf},
journal = {ICML},
pages = {1017--1024},
title = {{Kernel predictive linear Gaussian models for nonlinear stochastic dynamical systems}},
url = {http://dl.acm.org/citation.cfm?id=1143972},
year = {2006}
}
@article{Basharat2009,
author = {Basharat, Arslan and Shah, M},
booktitle = {IEEE International Conference on Comuter Vision},
file = {:C$\backslash$:/Users/arunvenk/Dropbox/CMU/Research/LearningInverseRobots/Lit/SysID/Time Series Modeling (Chaos).pdf:pdf},
isbn = {9781424444199},
pages = {1941--1948},
title = {{Time series prediction by chaotic modeling of nonlinear dynamical systems}},
url = {http://ieeexplore.ieee.org/xpls/abs\_all.jsp?arnumber=5459429},
year = {2009}
}
@inproceedings{Gijsberts2011,
address = {Shanghai},
author = {Gijsberts, Arjan and Metta, Giorgio},
booktitle = {IEEE International Conference on Robotics and Automation},
doi = {10.1109/ICRA.2011.5980191},
file = {:C$\backslash$:/Users/arunvenk/Dropbox/CMU/Research/LearningInverseRobots/Lit/SysID/learning/Incremental Learning of Robot Dynamics using Random Features.pdf:pdf},
isbn = {978-1-61284-386-5},
month = may,
pages = {951--956},
publisher = {Ieee},
title = {{Incremental learning of robot dynamics using random features}},
url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=5980191 http://ieeexplore.ieee.org/xpls/abs\_all.jsp?arnumber=5980191},
year = {2011}
}
@article{Chaudhry2009,
author = {Chaudhry, R. and Ravichandran, A. and Hager, G. and Vidal, R.},
doi = {10.1109/CVPR.2009.5206821},
isbn = {978-1-4244-3992-8},
journal = {IEEE Conference on Computer Vision and Pattern Recognition},
month = jun,
pages = {1932--1939},
publisher = {Ieee},
title = {{Histograms of oriented optical flow and Binet-Cauchy kernels on nonlinear dynamical systems for the recognition of human actions}},
year = {2009}
}
@article{Lopez-Paz2014,
archivePrefix = {arXiv},
arxivId = {arXiv:1402.0119v1},
author = {Lopez-Paz, D and Sra, Suvrit and Smola, A},
eprint = {arXiv:1402.0119v1},
file = {:C$\backslash$:/Users/arunvenk/Dropbox/CMU/Research/LearningInverseRobots/Lit/kernels/smola\_Randomized Nonlinear Component Analysis.pdf:pdf},
journal = {arXiv preprint arXiv:1402.0119},
title = {{Randomized Nonlinear Component Analysis}},
url = {http://arxiv.org/abs/1402.0119},
year = {2014}
}
@article{Kawahara2006,
abstract = {In this paper, we present a subspace method for learning nonlinear dynamical systems based on stochastic realization, in which state vectors are chosen using kernel canonical correlation analysis, and then state-space systems are identified through regression with the state vectors. We construct the theoretical underpin- ning and derive a concrete algorithm for nonlinear identification. The obtained algorithm needs no iterative optimization procedure and can be implemented on the basis of fast and reliable numerical schemes. The simulation result shows that our algorithm can express dynamics with a high degree of accuracy. 1},
author = {Kawahara, Yoshinobu and Yairi, Takehisa and Machida, Kazo},
file = {:C$\backslash$:/Users/arunvenk/Dropbox/CMU/Research/LearningInverseRobots/Lit/kernels/Kernel Subspace Method by Stochastic.pdf:pdf},
journal = {NIPS},
pages = {665--672},
title = {{A Kernel Subspace Method by Stochastic Realization for Learning Nonlinear Dynamical Systems}},
url = {http://ieeexplore.ieee.org/xpls/abs\_all.jsp?arnumber=6287311},
year = {2006}
}

@inproceedings{Gerstner1997,
address = {Berlin/Heidelberg},
author = {Sch\"{o}lkopf, Bernhard and Smola, Alex J and Muller, Klaus Robert},
booktitle = {Artificial Neural Networks — ICANN'97},
doi = {10.1007/BFb0020124},
editor = {Gerstner, Wulfram and Germond, Alain and Hasler, Martin and Nicoud, Jean-Daniel},
file = {:C$\backslash$:/Users/arunvenk/Dropbox/CMU/Research/LearningInverseRobots/Lit/kernels/scholkopf\_Kernel Principal Component Analysis.pdf:pdf},
isbn = {3-540-63631-5},
keywords = {kpca},
mendeley-tags = {kpca},
publisher = {Springer-Verlag},
series = {Lecture Notes in Computer Science},
title = {{Kernel Principal Components Analysis}},
url = {http://www.springerlink.com/index/10.1007/BFb0020124},
volume = {1327},
year = {1997}
}

@book{van2012subspace,
  title={Subspace identification for linear systems: {Theory—Implementation—Applications}},
  author={Van Overschee, Peter and De Moor, BL},
  year={2012},
  publisher={Springer Science \& Business Media}
}


@article{bagnelllearning,
  title={Learning Deep Inference Machines},
  author={Bagnell, J Andrew and Grubb, Alex and Munoz, Daniel and Ross, Stephane},
  journal = {The Learning Workshop},
  year = {2010}
}

@article{Chan2007,
author = {Chan, Antoni B. and Vasconcelos, Nuno},
journal = {IEEE Conference on Computer Vision and Pattern Recognition},
month = jun,
pages = {1--6},
publisher = {Ieee},
title = {{Classifying Video with Kernel Dynamic Textures}},
year = {2007}
}

@inproceedings{langford2009learning,
  title={Learning nonlinear dynamic models},
  author={Langford, John and Salakhutdinov, Ruslan and Zhang, Tong},
  booktitle={Proceedings of the 26th International Conference on Machine Learning (ICML-09)},
  pages={75},
  year={2009}
}

@article{venkatraman2015improving,
  title={Improving multi-step prediction of learned time series models},
  author={Venkatraman, Arun and Hebert, Martial and Bagnell, J Andrew},
  journal={AAAI},
  year={2015}
}

@inproceedings{ross2010efficient,
  title={Efficient reductions for imitation learning},
  author={Ross, St{\'e}phane and Bagnell, J. Andrew},
  booktitle={AISTATS},
  pages={661--668},
  year={2010}
}


@article{tu2010,
  title={Auto-context and its application to high-level vision tasks and 3d brain image segmentation},
  author={Tu, Zhuowen and Bai, Xiang},
  journal={Pattern Analysis and Machine Intelligence, IEEE Transactions on},
  volume={32},
  number={10},
  pages={1744--1757},
  year={2010},
  publisher={IEEE}
}


@article{banerjee2005,
  title={On the optimality of conditional expectation as a Bregman predictor},
  author={Banerjee, Arindam and Guo, Xin and Wang, Hui},
  journal={Information Theory, IEEE Transactions on},
  volume={51},
  number={7},
  pages={2664--2669},
  year={2005},
  publisher={IEEE}
}

@article{daume2009search,
  title={Search-based structured prediction},
  author={Daum{\'e} III, Hal and Langford, John and Marcu, Daniel},
  journal={Machine learning},
  year={2009},
}

@article{jaeger2000observable,
  title={Observable operator models for discrete stochastic time series},
  author={Jaeger, Herbert},
  journal={Neural Computation},
  volume={12},
  number={6},
  pages={1371--1398},
  year={2000},
  publisher={MIT Press}
}


@inproceedings{rahimi2007,
  title={Random features for large-scale kernel machines},
  author={Rahimi, Ali and Recht, Benjamin},
  booktitle={Advances in neural information processing systems},
  pages={1177--1184},
  year={2007}
}

@article{Hazan2012_ICML,
author = {Hazan, Elad and Kale, Satyen},
file = {:usr0/home/wensun/Documents/ICML2015.bib:bib},
journal = {29th International Conference on Machine Learning (ICML 2012)},
pages = {521--528},
title = {{Projection-free Online Learning}},
year = {2012}
}

@article{srebro2010optimistic,
  title={Optimistic Rates for Learning with a Smooth Loss},
  author={Srebro, Nathan and Sridharan, Karthik and Tewari, Ambuj},
  journal={arXiv preprint arXiv:1009.3896},
  year={2010}
}

@inproceedings{NIPS2015_5673,
title = {Supervised Learning for Dynamical System Learning},
author = {Hefny, Ahmed and Downey, Carlton and Gordon, Geoffrey J},
booktitle = {Advances in Neural Information Processing Systems 28},
year = {2015}
}


@inproceedings{kulesza2014low,
  title={Low-rank spectral learning},
  author={Kulesza, Alex and Rao, N Raj and Singh, Satinder},
  booktitle={Proceedings of the 17th Conference on Artificial Intelligence and Statistics},
  year={2014}
}

@inproceedings{Venkatraman-AAAI-16,
   Author = {Arun Venkatraman and Wen Sun and Martial Hebert and J. Andrew Bagnell and Byron Boots},
   Title = {Online Instrumental Variable Regression with Applications to Online Linear System Identification},
  booktitle={AAAI},
  year={2016}
}


@book{wei1994time,
  title={Time series analysis},
  author={Wei, William Wu-Shyong},
  year={1994},
  publisher={Addison-Wesley publication}
}

@article{zeiler2012adadelta,
  title={ADADELTA: an adaptive learning rate method},
  author={Zeiler, Matthew D},
  journal={arXiv preprint arXiv:1212.5701},
  year={2012}
}
@article{tieleman2012lecture,
  title={Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude},
  author={Tieleman, Tijmen and Hinton, Geoffrey},
  journal={COURSERA: Neural Networks for Machine Learning},
  volume={4},
  pages={2},
  year={2012}
}

@article{duchi2011adaptive,
  title={Adaptive subgradient methods for online learning and stochastic optimization},
  author={Duchi, John and Hazan, Elad and Singer, Yoram},
  journal={JMLR},
  year={2011},
}

@incollection{ramakrishna2014pose,
  title={Pose machines: Articulated pose estimation via inference machines},
  author={Ramakrishna, Varun and Munoz, Daniel and Hebert, Martial and Bagnell, James Andrew and Sheikh, Yaser},
  booktitle={ECCV},
  year={2014},
  publisher={Springer}
}

@inproceedings{lin2015deeply,
  title={Deeply learning the messages in message passing inference},
  author={Lin, Guosheng and Shen, Chunhua and Reid, Ian and van den Hengel, Anton},
  booktitle={NIPS},
  pages={361--369},
  year={2015}
}


@book{mohri2012foundations,
  title={Foundations of machine learning},
  author={Mohri, Mehryar and Rostamizadeh, Afshin and Talwalkar, Ameet},
  year={2012},
  publisher={MIT press}
}

@article{roweis1999unifying,
  title={A unifying review of linear Gaussian models},
  author={Roweis, Sam and Ghahramani, Zoubin},
  journal={Neural computation},
  volume={11},
  number={2},
  pages={305--345},
  year={1999},
  publisher={MIT Press}
}


@MISC{Bastien-Theano-2012,
        author = {Bastien, Fr{\'{e}}d{\'{e}}ric and Lamblin, Pascal and Pascanu, Razvan and Bergstra, James and Goodfellow, Ian J. and Bergeron, Arnaud and Bouchard, Nicolas and Bengio, Yoshua},
         title = {Theano: new features and speed improvements},
          year = {2012},
  howpublished = {Deep Learning and Unsupervised Feature Learning NIPS 2012 Workshop},
}


@inproceedings{belanger2015linear,
  title={A Linear Dynamical System Model for Text},
  author={Belanger, David and Kakade, Sham},
  booktitle={ICML},
  year={2015}
}

@article{ross2014reinforcement,
  title={Reinforcement and imitation learning via interactive no-regret learning},
  author={Ross, Stephane and Bagnell, J Andrew},
  journal={arXiv preprint arXiv:1406.5979},
  year={2014}
}

@inproceedings{bagnell2003covariant,
  title={Covariant policy search},
  author={Bagnell, J Andrew and Schneider, Jeff},
  year={2003},
  organization={IJCAI}
}

@inproceedings{schulman2015trust,
  title={Trust Region Policy Optimization.},
  author={Schulman, John and Levine, Sergey and Abbeel, Pieter and Jordan, Michael I and Moritz, Philipp},
  booktitle={ICML},
  pages={1889--1897},
  year={2015}
}

@article{williams1992simple,
  title={Simple statistical gradient-following algorithms for connectionist reinforcement learning},
  author={Williams, Ronald J},
  journal={Machine learning},
  year={1992},
  publisher={Springer}
}

@article{jaksch2010near,
  title={Near-optimal regret bounds for reinforcement learning},
  author={Jaksch, Thomas and Ortner, Ronald and Auer, Peter},
  journal={JMLR},
  year={2010}
}

@inproceedings{kakade2002approximately,
  title={Approximately optimal approximate reinforcement learning},
  author={Kakade, Sham and Langford, John},
  booktitle={ICML},
  year={2002}
}

@article{kakade2002natural,
  title={A natural policy gradient},
  author={Kakade, Sham},
  journal={NIPS},
  year={2002},
}

@inproceedings{chang2015learning,
  title={Learning to Search Better than Your Teacher},
  author={Chang, Kai-wei and Krishnamurthy, Akshay and Agarwal, Alekh and Daume, Hal and Langford, John},
  booktitle={ICML},
  year={2015}
}

@inproceedings{duan2016benchmarking,
  title={Benchmarking deep reinforcement learning for continuous control},
  author={Duan, Yan and Chen, Xi and Houthooft, Rein and Schulman, John and Abbeel, Pieter},
  booktitle={ICML},
  year={2016}
}

@article{duyckpredicting,
  title={Predicting Structure in Handwritten Algebra Data From Low Level Features},
  author={Duyck, James A and Gordon, Geoffrey J},
  journal={Data Analysis Project Report, MLD, CMU},
  year = {2015}
}


@article{chang2015learning_dependency,
  title={Learning to search for dependencies},
  author={Chang, Kai-Wei and He, He and Daum{\'e} III, Hal and Langford, John},
  journal={arXiv preprint arXiv:1503.05615},
  year={2015}
}

@inproceedings{bengio2015scheduled,
  title={Scheduled sampling for sequence prediction with recurrent neural networks},
  author={Bengio, Samy and Vinyals, Oriol and Jaitly, Navdeep and Shazeer, Noam},
  booktitle={NIPS},
  year={2015}
}

@article{kahn2016plato,
  title={PLATO: Policy Learning using Adaptive Trajectory Optimization},
  author={Kahn, Gregory and Zhang, Tianhao and Levine, Sergey and Abbeel, Pieter},
  journal={arXiv preprint arXiv:1603.00622},
  year={2016}
}

@inproceedings{ho2016generative,
  title={Generative adversarial imitation learning},
  author={Ho, Jonathan and Ermon, Stefano},
  booktitle={NIPS},
  year={2016}
}

@inproceedings{finn2016guided,
  title={Guided cost learning: Deep inverse optimal control via policy optimization},
  author={Finn, Chelsea and Levine, Sergey and Abbeel, Pieter},
  booktitle={ICML},
  year={2016}
}
@article{brockman2016openai,
  title={OpenAI gym},
  author={Brockman, Greg and Cheung, Vicki and Pettersson, Ludwig and Schneider, Jonas and Schulman, John and Tang, Jie and Zaremba, Wojciech},
  journal={arXiv preprint arXiv:1606.01540},
  year={2016}
}

@inproceedings{ho2016model,
  title={Model-free imitation learning with policy optimization},
  author={Ho, Jonathan and Gupta, Jayesh K and Ermon, Stefano},
  booktitle={ICML},
  year={2016}
}

@inproceedings{abbeel2004apprenticeship,
  title={Apprenticeship learning via inverse reinforcement learning},
  author={Abbeel, Pieter and Ng, Andrew Y},
  booktitle={ICML},
  pages={1},
  year={2004},
  organization={ACM}
}

@inproceedings{ziebart2008maximum,
  title={Maximum Entropy Inverse Reinforcement Learning.},
  author={Ziebart, Brian D and Maas, Andrew L and Bagnell, J Andrew and Dey, Anind K},
  booktitle={AAAI},
  year={2008},
}

@inproceedings{syed2008apprenticeship,
  title={Apprenticeship learning using linear programming},
  author={Syed, Umar and Bowling, Michael and Schapire, Robert E},
  booktitle={ICML},
  year={2008},
}

@article{greensmith2004variance,
  title={Variance reduction techniques for gradient estimates in reinforcement learning},
  author={Greensmith, Evan and Bartlett, Peter L and Baxter, Jonathan},
  journal={JMLR},
  year={2004}
}

@inproceedings{sutskever2014sequence,
  title={Sequence to sequence learning with neural networks},
  author={Sutskever, Ilya and Vinyals, Oriol and Le, Quoc V},
  booktitle={NIPS},
  year={2014}
}

@article{kingma2014adam,
  title={Adam: A method for stochastic optimization},
  author={Kingma, Diederik and Ba, Jimmy},
  journal={arXiv preprint arXiv:1412.6980},
  year={2014}
}

@article{shalev2012online,
  title={Online learning and online convex optimization},
  author={Shalev-Shwartz, Shai and others},
  journal={Foundations and Trends{\textregistered} in Machine Learning},
  year={2012},
}

@inproceedings{sun2016learning,
  title={Learning to filter with predictive state inference machines},
  author={Sun, Wen and Venkatraman, Arun and Boots, Byron and Bagnell, J Andrew},
  booktitle={ICML},
  year={2016}
}

%author={Silver, David and Huang, Aja and Maddison, Chris J and Guez, Arthur and Sifre, Laurent and Van Den Driessche, George and Schrittwieser, Julian and Antonoglou, Ioannis and Panneershelvam, Veda and Lanctot, Marc and others},
@article{silver2016mastering,
  title={Mastering the game of Go with deep neural networks and tree search},
  author={Silver, David and others},
  journal={Nature},
  year={2016},
}

%author={Mnih, Volodymyr and Kavukcuoglu, Koray and Silver, David and Rusu, Andrei A and Veness, Joel and Bellemare, Marc G and Graves, Alex and Riedmiller, Martin and Fidjeland, Andreas K and Ostrovski, Georg and others},
@article{mnih2015human,
  title={Human-level control through deep reinforcement learning},
  author={Mnih, Volodymyr and others},
  journal={Nature},
  year={2015},
}

@article{bahdanau2016actor,
  title={An actor-critic algorithm for sequence prediction},
  author={Bahdanau, Dzmitry and Brakel, Philemon and Xu, Kelvin and Goyal, Anirudh and Lowe, Ryan and Pineau, Joelle and Courville, Aaron and Bengio, Yoshua},
  journal={arXiv preprint arXiv:1607.07086},
  year={2016}
}

@article{bubeck2015convex,
  title={Convex optimization: Algorithms and complexity},
  author={Bubeck, S{\'e}bastien and others},
  journal={Foundations and Trends{\textregistered} in Machine Learning},
  year={2015},
}

@article{bubeck2012regret,
  title={Regret analysis of stochastic and nonstochastic multi-armed bandit problems},
  author={Bubeck, S{\'e}bastien and Cesa-Bianchi, Nicolo and others},
  journal={Foundations and Trends{\textregistered} in Machine Learning},
  year={2012},
}


@article{phatak2002exploiting,
  title={Exploiting the connection between PLS, Lanczos methods and conjugate gradients: alternative proofs of some properties of PLS},
  author={Phatak, Aloke and de Hoog, Frank},
  journal={Journal of Chemometrics},
  year={2002},
}

@article{li2016deep,
  title={Deep reinforcement learning for dialogue generation},
  author={Li, Jiwei and Monroe, Will and Ritter, Alan and Galley, Michel and Gao, Jianfeng and Jurafsky, Dan},
  journal={arXiv preprint arXiv:1606.01541},
  year={2016}
}

@article{ranzato2015sequence,
  title={Sequence level training with recurrent neural networks},
  author={Ranzato, Marc'Aurelio and Chopra, Sumit and Auli, Michael and Zaremba, Wojciech},
  journal={ICLR 2016},
  year={2015}
}

@inproceedings{ross2013learning,
  title={Learning monocular reactive uav control in cluttered natural environments},
  author={Ross, St{\'e}phane and Melik-Barkhudarov, Narek and Shankar, Kumar Shaurya and Wendel, Andreas and Dey, Debadeepta and Bagnell, J Andrew and Hebert, Martial},
  booktitle={ICRA},
  year={2013},
}

@article{abbeel2010autonomous,
  title={Autonomous helicopter aerobatics through apprenticeship learning},
  author={Abbeel, Pieter and Coates, Adam and Ng, Andrew Y},
  journal={IJRR},
  year={2010},
  publisher={SAGE Publications}
}

@article{mulling2013learning,
  title={Learning to select and generalize striking movements in robot table tennis},
  author={M{\"u}lling, Katharina and Kober, Jens and Kroemer, Oliver and Peters, Jan},
  journal={IJRR},
  year={2013},
  publisher={SAGE Publications}
}

@inproceedings{ross2013contextual,
  title={Learning Policies for Contextual Submodular Prediction},
  author={Ross, Stephane and Zhou, Jiaji and Yue, Yisong and Dey, Debadeepta and Bagnell, Drew},
  booktitle={ICML},
  year={2013}
}

@inproceedings{ratliff2006maximum,
  title={Maximum margin planning},
  author={Ratliff, Nathan D and Bagnell, J Andrew and Zinkevich, Martin A},
  booktitle={ICML},
  year={2006},
}

@inproceedings{rhinehart2015visual,
  title={Visual chunking: A list prediction framework for region-based object detection},
  author={Rhinehart, Nicholas and Zhou, Jiaji and Hebert, Martial and Bagnell, J Andrew},
  booktitle={ICRA},
  year={2015},
  organization={IEEE}
}