Mathematical Machine Learning
Head:
Guido Montúfar (Email)
Phone:
+49 (0) 341 - 9959 - 880
Fax:
+49 (0) 341 - 9959 - 658
Address:
Inselstr. 22
04103 Leipzig
Publications Guido Montufar (sorted by year)
Mareike Dressler ; Marina Garrote-López ; Guido Montúfar ; Kemal Rose and Johannes Müller:
Algebraic optimization of sequential decision problems
In: Journal of symbolic computation,
121 (2024), 102241
Bibtex DOI: 10.1016/j.jsc.2023.102241 ARXIV: https://arxiv.org/abs/2211.09439Johannes Rauh ; Pradeep Kumar Banerjee ; Eckehard Olbrich ; Guido Montúfar and Jürgen Jost:
Continuity and additivity properties of information decompositions
In: International journal of approximate reasoning,
161 (2023), 108979
Bibtex DOI: 10.1016/j.ijar.2023.108979 ARXIV: https://arxiv.org/abs/2204.10982Hanna Tseran and Guido Montúfar:
Expected gradients of maxout networks and consequences to parameter initialization
Repository Open AccessKathlén Kohn ; Guido Montúfar ; Vahid Shahverdi and Matthew Trager:
Function space and critical points of linear convolutional networks
Repository Open AccessJohannes Müller and Guido Montúfar:
Geometry and convergence of natural policy gradient methods
In: Information geometry,
Vol. not yet known, pp. not yet known
Bibtex MIS-Preprint: 31/2022 DOI: 10.1007/s41884-023-00106-z ARXIV: https://arxiv.org/abs/2211.02105Kedar Karhadkar ; Michael Murray ; Hanna Tseran and Guido Montúfar:
Mildly overparameterized ReLU networks have a favorable loss landscape
Repository Open AccessThomas Merkh and Guido Montúfar:
Stochastic feedforward neural networks : universal approximation
In: Mathematical aspects of deep learning / Philipp Grohs... (eds.)
Bibtex DOI: 10.1017/9781009025096.007 ARXIV: https://arxiv.org/abs/1910.09763Cambridge : Cambridge University Press, 2023. - P. 267-313
Yanan Wang ; Yu Guang Wang ; Changyuan Hu ; Ming Li ; Yanan Fan ; Nina Otter ; Ikuan Sam ; Hongquan Gou ; Yiqun Hu ; Terry Kwok ; John Zalcberg ; Alex Boussioutas ; Roger J. Daly ; Guido Montúfar ; Pietro Lió ; Dakang Xu ; Geoffrey I. Webb and Jiangning Song:
Cell graph neural networks enable the digital staging of tumor microenvironment and
precise prediction of patient survival in gastric cancer
In: npj precision oncology,
6 (2022) 1, 45
Bibtex DOI: 10.1038/s41698-022-00285-5 LINK: https://www.medrxiv.org/content/10.1101/2021.09.01.21262086v2Michael Murray ; Hui Jin ; Benjamin Bowman and Guido Montúfar:
Characterizing the spectrum of the NTK via a power series expansion
Repository Open AccessAlex Tong Lin ; Mark J. Debord ; Katia Estabridis ; Gary Hewer ; Guido Montúfar and Stanley Osher:
Decentralized multi-agents by imitations of a centralized controller
In: 2nd annual conference on mathematical and scientific machine learning : 16-19 August
2021, virtual conference
[s. l.] : PMLR, 2022. - P. 619-651
(Proceedings of machine learning research ; 145)
Bibtex ARXIV: https://arxiv.org/abs/1902.02311 LINK: https://proceedings.mlr.press/v145/lin22a.htmlGuido Montúfar and Yu Guang Wang:
Distributed learning via filtered hyperinterpolation on manifolds
In: Foundations of computational mathematics,
22 (2022) 4, p. 1219-1271
Bibtex MIS-Preprint: 79/2020 DOI: 10.1007/s10208-021-09529-5 ARXIV: https://arxiv.org/abs/2007.09392Laura Escobar ; Patricio Gallardo ; Javier González-Anaya ; José L. Gonzáles ; Guido Montúfar and Alejandro H. Morales:
Enumeration of max-pooling responses with generalized permutohedra
Repository Open AccessKedar Karhadkar ; Pradeep Kumar Banerjee and Guido Montúfar:
FoSR : first-order spectral rewiring for addressing oversquashing in GNNs
Repository Open AccessKathlén Kohn ; Thomas Merkh ; Guido Montúfar and Matthew Trager:
Geometry of linear convolutional networks
In: SIAM journal on applied algebra and geometry,
6 (2022) 3, p. 368-406
Bibtex DOI: 10.1137/21M1441183 ARXIV: https://arxiv.org/abs/2108.01538Benjamin Bowman and Guido Montúfar:
Implicit bias of MSE gradient optimization in underparameterized neural networks
Repository Open AccessRenata Turkeš ; Guido Montúfar and Nina Otter:
On the effectiveness of persistent homology
In: Advances in neural information processing systems 35 : NeurIPS 2022 ; annual conference
on neural information processing systems 2022
Bibtex ARXIV: https://arxiv.org/abs/2206.10551 LINK: https://proceedings.neurips.cc/paper_files/paper/2022/hash/e637029c42aa593850eeebf46616444d-Abstract-Conference.html2022. - P. 35432-35448
Pradeep Kumar Banerjee ; Kedar Karhadkar ; Yu Guang Wang ; Uri Alon and Guido Montúfar:
Oversquashing in GNNs through the lens of information contraction and graph expansion
In: 2022 58th Annual Allerton Conference on communication, control, and computing : 27-30
Sept. 2022
Bibtex MIS-Preprint: 24/2022 DOI: 10.1109/ALLERTON49937.2022.9929363 ARXIV: https://arxiv.org/abs/2208.03471Piscataway, N.J. : IEEE, 2022
Guido Montúfar ; Yue Ren and Leon Zhang:
Sharp bounds for the number of regions of maxout networks and vertices of Minkowski
sums
In: SIAM journal on applied algebra and geometry,
6 (2022) 4, p. 618-649
Bibtex MIS-Preprint: 11/2021 DOI: 10.1137/21M1413699 ARXIV: https://arxiv.org/abs/2104.08135Johannes Müller and Guido Montúfar:
Solving infinite-horizon POMDPs with memoryless stochastic policies in state-action
space
Repository Open AccessBenjamin Bowman and Guido Montúfar:
Spectral bias outside the training set for deep networks in the kernel regime
In: Advances in neural information processing systems 35 : NeurIPS 2022 ; annual conference
on neural information processing systems 2022
Bibtex ARXIV: https://arxiv.org/abs/2206.02927 LINK: https://proceedings.neurips.cc/paper_files/paper/2022/hash/c4006ff54a7bbda74c09bad6f7586f5b-Abstract-Conference.html2022. - P. 30362-30377
Johannes Müller and Guido Montúfar:
The geometry of memoryless stochastic policy optimization in infinite-horizon POMDPs
In: ICLR 2022 : Tenth international conference on learning representations ; 25th April
2022
Bibtex MIS-Preprint: 22/2021 ARXIV: https://arxiv.org/abs/2110.07409 LINK: https://openreview.net/forum?id=A05I5IvrdL-[s. l.] : ICLR, 2022. - P. 1-45
Alex Tong Lin ; Guido Montúfar and Stanley Osher:
A top-down approach to attain decentralized multi-agents
In: Handbook of reinforcement learning and control / Kyriakos G. Vamvoudakis... (eds.)
Cham : Springer, 2021. - P. 419-431
(Studies in systems, decision and control ; 325)
Bibtex DOI: 10.1007/978-3-030-60990-0_14Xuebin Zheng ; Bingxin Zhou ; Junbin Gao ; Yu Guang Wang ; Pietro Lió ; Ming Li and Guido Montúfar:
How framelets enhance graph neural networks
In: ICML 2021 : Proceedings of the 38th international conference on machine learning ;
18-24 July 2021
[s. l.] : PMLR, 2021. - P. 12761-12771
(Proceedings of machine learning research ; 139)
Bibtex ARXIV: https://arxiv.org/abs/2102.06986 LINK: https://proceedings.mlr.press/v139/zheng21c.htmlPradeep Kumar Banerjee and Guido Montúfar:
Information complexity and generalization bounds
In: IEEE international symposium on information theory (ISIT) from 12 - 20 July 2021 ;
Melbourne, Victoria, Australia
Bibtex DOI: 10.1109/ISIT45174.2021.9517960 ARXIV: https://arxiv.org/abs/2105.01747Piscataway, NY : IEEE, 2021. - P. 676-681
Hui Jin ; Pradeep Kumar Banerjee and Guido Montúfar:
Learning curves for Gaussian process regression with power-law priors and targets
Repository Open AccessHanna Tseran and Guido Montúfar:
On the expected complexity of maxout networks
In: Advances in neural information processing systems 34 : NeurIPS 2021 ; annual conference
on neural information processing systems 2021, December 6-14, 2021, virtual / Marc'Aurelio Ranzato (ed.)
Bibtex MIS-Preprint: 18/2021 ARXIV: https://arxiv.org/abs/2107.00379 LINK: https://proceedings.neurips.cc/paper/2021/hash/f2c3b258e9cd8ba16e18f319b3c88c66-Abstract.html2021. - P. 28995-29008
Pradeep Kumar Banerjee and Guido Montúfar:
PAC-bayes and information complexity
In: ICLR 2021 workshop on neural compression : from information theory to applications
Bibtex MIS-Preprint: 21/2021 LINK: https://openreview.net/forum?id=LPw-isa6Ngb[s. l.] : ICLR, 2021. - P. 1-15
Quynh Nguyen ; Marco Mondelli and Guido Montúfar:
Tight bounds on the smallest eigenvalue of the neural tangent kernel for deep ReLU
networks
In: ICML 2021 : Proceedings of the 38th international conference on machine learning ;
18-24 July 2021
[s. l.] : PMLR, 2021. - P. 8119-8129
(Proceedings of machine learning research ; 139)
Bibtex ARXIV: https://arxiv.org/abs/2012.11654 LINK: https://proceedings.mlr.press/v139/nguyen21g.htmlDohyun Kwon ; Yeoneung Kim ; Guido Montúfar and Insoon Yang:
Training Wasserstein GANs without gradient penalties
Repository Open AccessTürkü Özlüm Celik ; Asgar Jamneshan ; Guido Montúfar ; Bernd Sturmfels and Lorenzo Venturello:
Wasserstein distance to independence models
In: Journal of symbolic computation,
104 (2021), p. 855-873
Bibtex DOI: 10.1016/j.jsc.2020.10.005 ARXIV: https://arxiv.org/abs/2003.06725Alex Tong Lin ; Wuchen Li ; Stanley Osher and Guido Montúfar:
Wasserstein proximal of GANs
In: Geometric science of information : 5th international conference, GSI 2021, Paris,
France, July 21-23, 2021, proceedings / Frank Nielsen... (eds.)
Cham : Springer, 2021. - P. 524-533
(Lecture notes in computer science ; 12829)
Bibtex MIS-Preprint: 88/2018 DOI: 10.1007/978-3-030-80209-7_57 ARXIV: https://arxiv.org/abs/2102.06862Christian Bodnar ; Fabrizio Frasca ; Nina Otter ; Yu Guang Wang ; Pietro Lió ; Guido Montúfar and Michael Bronstein:
Weisfeiler and Lehman go cellular : CW networks
In: Advances in neural information processing systems 34 : NeurIPS 2021 ; annual conference
on neural information processing systems 2021, December 6-14, 2021, virtual / Marc'Aurelio Ranzato (ed.)
Bibtex ARXIV: https://arxiv.org/abs/2106.12575 LINK: https://proceedings.neurips.cc/paper/2021/hash/157792e4abb490f99dbd738483e0d2d4-Abstract.html2021. - P. 2625-2640
Christian Bodnar ; Fabrizio Frasca ; Yu Guang Wang ; Nina Otter ; Guido Montúfar ; Pietro Lió and Michael Bronstein:
Weisfeiler and Lehman go topological : message passing simplicial networks
In: ICML 2021 : Proceedings of the 38th international conference on machine learning ;
18-24 July 2021
[s. l.] : PMLR, 2021. - P. 1026-1037
(Proceedings of machine learning research ; 139)
Bibtex ARXIV: https://arxiv.org/abs/2103.03212 LINK: https://proceedings.mlr.press/v139/bodnar21a.htmlMichael Arbel ; Arthur Gretton ; Wuchen Li and Guido Montúfar:
A Pytorch implementation of the KWNG estimator [Computer code]
Bibtex ARXIV: https://arxiv.org/abs/1910.09652 LINK: https://openreview.net/pdf?id=Hklz71rYvS CODE: https://github.com/MichaelArbel/KWNG
Repository Open AccessGuido Montúfar ; Nina Otter and Yu Guang Wang:
Can neural networks learn persistent homology features?
In: NeurIPS 2020 : Workshop on topological data analysis and beyond ; 11 December 2020
Bibtex ARXIV: https://arxiv.org/abs/2011.14688 LINK: https://openreview.net/forum?id=pqpXM1Wjsxe2020
Pradeep Kumar Banerjee ; Johannes Rauh and Guido Montúfar:
computeUI [Computer code]
Bibtex ARXIV: https://arxiv.org/abs/1709.07487 LINK: https://www.mdpi.com/1099-4300/16/4/2161 CODE: https://github.com/infodeco/computeUI
Repository Open AccessThomas Merkh and Guido Montúfar:
Factorized mutual information maximization
In: Kybernetika,
56 (2020) 5, p. 948-978
Bibtex DOI: 10.14736/kyb-2020-5-0948 ARXIV: https://arxiv.org/abs/1906.05460Yu Guang Wang ; Ming Li ; Zheng Ma ; Guido Montúfar ; Xiaosheng Zhuang and Yanan Fan:
Haar graph pooling
In: ICML 2020 : Proceedings of the 37th international conference on machine learning ;
13-18 July 2020
[s. l.] : PMLR, 2020. - P. 9952-9962
(Proceedings of machine learning research ; 119)
Bibtex MIS-Preprint: 72/2020 ARXIV: https://arxiv.org/abs/1909.11580 LINK: http://proceedings.mlr.press/v119/wang20m.html CODE: https://github.com/YuGuangWang/HaarPoolHui Jin and Guido Montúfar:
Implicit bias of gradient descent for mean squared error regression with wide neural
networks
Bibtex MIS-Preprint: 63/2020 ARXIV: https://arxiv.org/abs/2006.07356
Repository Open AccessMichael Arbel ; Arthur Gretton ; Wuchen Li and Guido Montúfar:
Kernelized Wasserstein natural gradient
In: ICLR 2020 : Eighth international conference on learning representations ; Millennium
Hall, Addis Ababa, Ethiopia ; 26th-30th April 2020
Bibtex ARXIV: https://arxiv.org/abs/1910.09652 LINK: https://openreview.net/pdf?id=Hklz71rYvS CODE: https://github.com/MichaelArbel/KWNG[s. l.] : ICLR, 2020. - P. 1-31
Türkü Özlüm Celik ; Asgar Jamneshan ; Guido Montúfar ; Bernd Sturmfels and Lorenzo Venturello:
Optimal transport to a variety
In: Mathematical aspects of computer and information sciences : 8th international conference,
MACIS 2019, Gebze-Istanbul, Turkey, November 13-15, 2019 ; revised selected papers / Daniel Slamanig... (eds.)
Cham : Springer, 2020. - P. 364-381
(Lecture notes in computer science ; 11989)
Bibtex MIS-Preprint: 7/2021 DOI: 10.1007/978-3-030-43120-4_29 ARXIV: https://arxiv.org/abs/1909.11716Yonatan Dukler ; Quanquan Gu and Guido Montúfar:
Optimization theory for ReLU neural networks trained with normalization layers
In: ICML 2020 : Proceedings of the 37th international conference on machine learning ;
13-18 July 2020
[s. l.] : PMLR, 2020. - P. 2751-2760
(Proceedings of machine learning research ; 119)
Bibtex MIS-Preprint: 64/2020 ARXIV: https://arxiv.org/abs/2006.06878 LINK: http://proceedings.mlr.press/v119/dukler20a.htmlWuchen Li and Guido Montúfar:
Ricci curvature for parametric statistics via optimal transport
In: Information geometry,
3 (2020) 1, p. 89-117
Bibtex DOI: 10.1007/s41884-020-00026-2 ARXIV: https://arxiv.org/abs/1807.07095Pradeep Kumar Banerjee and Guido Montúfar:
The variational deficiency bottleneck
In: Proceedings of the international joint conference on neural networks 2020 (IJCNN)
Bibtex DOI: 10.1109/IJCNN48605.2020.9206900 ARXIV: https://arxiv.org/abs/1810.11677Piscataway, NJ : IEEE Operations Center, 2020. - P. 1-8
Yonatan Dukler ; Wuchen Li ; Alex Tong Lin and Guido Montúfar:
Wasserstein of Wasserstein loss for generative models - WWGAN [Computer code]
Bibtex MIS-Preprint: 13/2019 LINK: http://proceedings.mlr.press/v97/dukler19a.html CODE: https://github.com/dukleryoni/WWGAN
Repository Open AccessNihat Ay ; Johannes Rauh and Guido Montúfar:
A continuity result for optimal memoryless planning in POMDPs
In: RLDM 2019 : 4th multidisciplinary conference on reinforcement learning and decision
making ; July 7-10, 2019 ; Montréal, Canada
Bibtex MIS-Preprint: 5/2021 LINK: http://rldm.org/papers/extendedabstracts.pdf#page=362Montréal, Canada : University, 2019. - P. 362-365
Wuchen Li ; Alex Tong Lin and Guido Montúfar:
Affine natural proximal learning
In: Geometric science of information : 4th international conference, GSI 2019, Toulouse,
France, August 27-29, 2019, proceedings / Frank Nielsen... (eds.)
Cham : Springer, 2019. - P. 705-714
(Lecture notes in computer science ; 11712)
Bibtex MIS-Preprint: 6/2021 DOI: 10.1007/978-3-030-26980-7_73 LINK: https://www.researchgate.net/publication/331162910Guido Montúfar:
Computing the unique information - 1st workshop on semantic information - CVPR June
2019 - Long Beach [Slides]
Repository Open AccessGuido Montúfar:
Contoursurf [Computer code]
Repository Open AccessPradeep Kumar Banerjee ; Sumukh Bansal ; Ilke Demir ; Minh Ha Quang ; Lin Huang ; Ruben Hühnerbein ; Scott C. James ; Oleg Kachan ; Louis Ly ; Marius Lysaker ; Samee Maharjan ; Anton Mallasto ; Guido Montúfar ; Kai Sandfort ; Stefan C. Schonsheck ; Pablo Suárez-Serrato ; Katarína Tóthová ; Yu Guang Wang ; Jia Le Xian and Rui Xiang:
Geometry and learning from data in 3D and beyond : IPAM long program, Spring 2019
[Report]
Repository Open AccessAnton Mallasto ; Guido Montúfar and Augusto Gerolin:
How well do WGANs estimate the Wasserstein metric?
Repository Open AccessGuido Montúfar ; Johannes Rauh and Nihat Ay:
Task-agnostic constraining in average reward POMDPs
In: Task-agnostic reinforcement learning : workshop at ICLR, 06 May 2019, New Orleans
Bibtex MIS-Preprint: 9/2021 LINK: https://tarl2019.github.io/assets/papers/montufar2019taskagnostic.pdf2019
Alex Tong Lin ; Yonatan Dukler ; Wuchen Li and Guido Montúfar:
Wasserstein diffusion Tikhonov regularization
In: NeurIPS 2019 : Workshop on optimal transport and machine learning ; Vancouver, December
13 2019
Bibtex ARXIV: https://arxiv.org/abs/1909.06860 LINK: https://sites.google.com/view/otml2019/home2019
Guido Montúfar:
Wasserstein information geometry for learning from data : tutorial at geometry and
learning from data, IPAM, March 2019 [Slides]
Repository Open AccessYonatan Dukler ; Wuchen Li ; Alex Tong Lin and Guido Montúfar:
Wasserstein of Wasserstein loss for learning generative models
In: Proceedings of the 36th international conference on machine learning, 9-15 June 2019,
Long Beach, California, USA / Kamalika Chaudhuri (ed.)
Long Beach, California : PMLR, 2019. - P. 1716-1725
(Proceedings of machine learning research ; 97)
Bibtex MIS-Preprint: 13/2019 LINK: http://proceedings.mlr.press/v97/dukler19a.html CODE: https://github.com/dukleryoni/WWGANPradeep Kumar Banerjee ; Johannes Rauh and Guido Montúfar:
Computing the unique information
In: IEEE international symposium on information theory (ISIT) from June 17 to 22, 2018
at the Talisa Hotel in Vail, Colorado, USA
Bibtex MIS-Preprint: 73/2017 DOI: 10.1109/ISIT.2018.8437757 ARXIV: https://arxiv.org/abs/1709.07487 CODE: https://github.com/infodeco/computeUIPiscataway, NY : IEEE, 2018. - P. 141-145
Guido Montúfar:
Illustration of maxout layer upper bound [Suppl. to: On the number of linear regions
of deep neural networks]
Repository Open AccessAnna Seigal and Guido Montúfar:
Mixtures and products in two graphical models
In: Journal of algebraic statistics,
9 (2018) 1, p. 1-20
Bibtex DOI: 10.18409/jas.v9i1.90 ARXIV: https://arxiv.org/abs/1709.05276Wuchen Li and Guido Montúfar:
Natural gradient via optimal transport
In: Information geometry,
1 (2018) 2, p. 181-214
Bibtex DOI: 10.1007/s41884-018-0015-3 ARXIV: https://arxiv.org/abs/1803.07033Guido Montúfar:
Restricted Boltzmann machines : introduction and review
In: Information geometry and its applications : on the occasion of Shun-ichi Amari's 80th
Birthday, IGAIA IV Liblice, Czech Republic, June 2016 / Nihat Ay... (eds.)
Cham : Springer, 2018. - P. 75-115
(Springer proceedings in mathematics and statistics ; 252)
Bibtex MIS-Preprint: 87/2018 DOI: 10.1007/978-3-319-97798-0_4 ARXIV: https://arxiv.org/abs/1806.07066Guido Montúfar ; Johannes Rauh and Nihat Ay:
Uncertainty and stochasticity of optimal policies
In: Proceedings of the 11th workshop on uncertainty processing WUPES '18, June 6-9, 2018 / Václav Kratochvíl (ed.)
Bibtex MIS-Preprint: 8/2021 LINK: http://wupes.utia.cas.cz/proceedings/proceedings.pdfPraha : MatfyzPress, 2018. - P. 133-140
Guido Montúfar and Jason Morton:
Dimension of marginals of Kronecker product models
In: SIAM journal on applied algebra and geometry,
1 (2017) 1, p. 126-151
Bibtex MIS-Preprint: 75/2015 DOI: 10.1137/16M1077489 ARXIV: http://arxiv.org/abs/1511.03570Guido Montúfar and Johannes Rauh:
Geometry of policy improvement
In: Geometric science of information : Third International Conference, GSI 2017, Paris,
France, November 7-9, 2017, proceedings / Frank Nielsen... (eds.)
Cham : Springer, 2017. - P. 282-290
(Lecture notes in computer science ; 10589)
Bibtex DOI: 10.1007/978-3-319-68445-1_33 ARXIV: https://arxiv.org/abs/1704.01785Guido Montúfar and Johannes Rauh:
Hierarchical models as marginals of hierarchical models
In: International journal of approximate reasoning,
88 (2017), p. 531-546
Bibtex MIS-Preprint: 27/2016 DOI: 10.1016/j.ijar.2016.09.003 ARXIV: http://arxiv.org/abs/1508.03606Keyan Ghazi-Zahedi ; Raphael Deimel ; Guido Montúfar ; Vincent Wall and Oliver Brock:
Morphological computation : the good, the bad, and the ugly
In: 2017 IEEE/RSJ international conference on intelligent robots and systems (IROS) :
Vancouver, BC, Canada ; September 24-28, 2017
Bibtex DOI: 10.1109/IROS.2017.8202194 LINK: https://www.researchgate.net/publication/318710693New York, NY : IEEE, 2017. - P. 464-469
Guido Montúfar:
Notes on the number of linear regions of deep neural networks
In: 2017 international conference on sampling theory and applications (SampTA) / Gholamreza Anbarjafari... (eds.)
Bibtex LINK: https://www.researchgate.net/publication/322539221Piscataway, NJ : IEEE, 2017. - P. 156-159
Guido Montúfar ; Jason Morton and Johannes Rauh:
Restricted Boltzmann machines [In: Algebraic statistics ; 16 April - 22 April 2017
; report no. 20/2017]
In: Oberwolfach reports,
14 (2017) 2, p. 1241-1242
Bibtex DOI: 10.4171/OWR/2017/20 LINK: https://publications.mfo.de/handle/mfo/3584Guido Montúfar ; Keyan Ghazi-Zahedi and Nihat Ay:
Stochasticity of optimal policies for POMDPs
In: RLDM 2017 : 3rd multidisciplinary conference on reinforcement learning and decision
making ; June 11-14, 2017 ; Ann Arbor, Michigan, USA
Bibtex LINK: http://rldm.org/wp-content/uploads/2017/06/RLDM17AbstractsBooklet.pdfMichigan : University, 2017
Keyan Ghazi-Zahedi ; Daniel F. B. Haeufle ; Guido Montúfar ; Syn Schmitt and Nihat Ay:
Evaluating morphological computation in muscle and DC-motor driven models of hopping
movements
In: Frontiers in robotics and AI,
3 (2016), 42
Bibtex DOI: 10.3389/frobt.2016.00042 ARXIV: http://arxiv.org/abs/1512.00250Guido Montúfar:
Geometry of Boltzmann machines
In: International conference on information geometry and its applications IV : Liblice,
June 12-17, 2016 ; in honor of Shun-ichi Amari / Nihat Ay... (eds.)
Bibtex MIS-Preprint: 87/2018 ARXIV: https://arxiv.org/abs/1806.07066Praha : Matfyzpress, 2016. - P. 25-25
Guido Montúfar ; Keyan Ghazi-Zahedi and Nihat Ay:
Information theoretically aided reinforcement learning for embodied agents
Repository Open AccessGuido Montúfar and Johannes Rauh:
Mode poset probability polytopes
In: Journal of algebraic statistics,
7 (2016) 1, p. 1-13
Bibtex MIS-Preprint: 22/2015 DOI: 10.18409/jas.v7i1.41 ARXIV: http://arxiv.org/abs/1503.00572Guido Montúfar:
A comparison of neural network architectures
In: Deep learning Workshop, ICML '15, Vauban Hall at Lille Grande Palais, France, July
10 and 11, 2015
Bibtex LINK: https://www.researchgate.net/publication/332767274Guido Montúfar ; Keyan Ghazi-Zahedi and Nihat Ay:
A theory of cheap control in embodied systems
In: PLoS computational biology,
11 (2015) 9, e1004427
Bibtex MIS-Preprint: 70/2014 DOI: 10.1371/journal.pcbi.1004427 ARXIV: http://arxiv.org/abs/1407.6836Guido Montúfar:
Deep narrow Boltzmann machines are universal approximators
In: Third international conference on learning representations - ICLR 2015 : May 7-9 2015,
San Diego, CA. USA
Bibtex MIS-Preprint: 113/2014 ARXIV: http://arxiv.org/abs/1411.3784 LINK: https://iclr.cc/archive/www/2015.htmlSan Diego : ICLR, 2015
Guido Montúfar and Jason Morton:
Discrete restricted Boltzmann machines
In: Journal of machine learning research,
16 (2015), p. 653-672
Bibtex MIS-Preprint: 106/2014 ARXIV: http://arxiv.org/abs/1301.3529 LINK: http://jmlr.org/papers/v16/montufar15a.htmlGuido Montúfar ; Keyan Ghazi-Zahedi and Nihat Ay:
Geometry and determinism of optimal stationary control in partially observable Markov
decision processes
Bibtex MIS-Preprint: 22/2016 ARXIV: http://arxiv.org/abs/1503.07206
Repository Open AccessGuido Montúfar ; Nihat Ay and Keyan Ghazi-Zahedi:
Geometry and expressive power of conditional restricted Boltzmann machines
In: Journal of machine learning research,
16 (2015), p. 2405-2436
Bibtex MIS-Preprint: 16/2014 ARXIV: http://arxiv.org/abs/1402.3346 LINK: http://www.jmlr.org/papers/v16/montufar15b.htmlGuido Montúfar and Johannes Rauh:
Hierarchical models as marginals of hierarchical models
In: Proceedings of the 10th workshop on uncertainty processing WUPES '15, Moninec, Czech
Republic, September 16-19, 2015 / Václav Kratochvíl (ed.)
Bibtex MIS-Preprint: 27/2016 ARXIV: http://arxiv.org/abs/1508.03606 LINK: http://wupes.fm.vse.cz/2015/data/Proceedings.pdfPraha : Oeconomica, 2015. - P. 131-145
Guido Montúfar and Johannes Rauh:
Mode poset probability polytopes
In: Proceedings of the 10th workshop on uncertainty processing WUPES '15, Moninec, Czech
Republic, September 16-19, 2015 / Václav Kratochvíl (ed.)
Bibtex MIS-Preprint: 22/2015 ARXIV: http://arxiv.org/abs/1503.00572 LINK: http://wupes.fm.vse.cz/2015/data/Proceedings.pdfPraha : Oeconomica, 2015. - P. 147-154
Guido Montúfar:
Universal approximation of Markov kernels by shallow stochastic feedforward networks
Bibtex MIS-Preprint: 23/2015 ARXIV: http://arxiv.org/abs/1503.07211
Repository Open AccessGuido Montúfar and Jason Morton:
When does a mixture of products contain a product of mixtures?
In: SIAM journal on discrete mathematics,
29 (2015) 1, p. 321-347
Bibtex MIS-Preprint: 98/2014 DOI: 10.1137/140957081 ARXIV: http://arxiv.org/abs/1206.0387Guido Montúfar and Jason Morton:
Geometry of hidden-visible products of statistical models
In: Algebraic Statistics 2014 : May 19-22
Bibtex LINK: http://mypages.iit.edu/~as2014/abstracts.html#MontufarChicago, IL : Illinois Institute of Technology, 2014
Guido Montúfar ; Johannes Rauh and Nihat Ay:
On the Fisher metric of conditional probability polytopes
In: Entropy,
16 (2014) 6, p. 3207-3233
Bibtex MIS-Preprint: 87/2014 DOI: 10.3390/e16063207 ARXIV: http://arxiv.org/abs/1404.0198Razvan Pascanu ; Guido Montúfar and Yoshua Bengio:
On the number of inference regions of deep feed forward networks with piece-wise linear
activations
In: Second international conference on learning representations - ICLR 2014 : 14-16 April
2014, Banff, Canada
Bibtex MIS-Preprint: 72/2014 ARXIV: http://arxiv.org/abs/1312.6098 LINK: https://openreview.net/group?id=ICLR.cc/2014/conferenceBanff : ICLR, 2014
Guido Montúfar ; Razvan Pascanu ; Kyunghyun Cho and Yoshua Bengio:
On the number of linear regions of deep neural networks
In: NIPS 2014 : Proceedings of the 27th international conference on neural information
processing systems - volume 2 ; Montreal, Quebec, Canada, December 8th-13th
Bibtex MIS-Preprint: 73/2014 ARXIV: http://arxiv.org/abs/1402.1869 LINK: https://papers.nips.cc/paper/5422-on-the-number-of-linear-regions-of-deep-neural-networksCambridge, MA : MIT Press, 2014. - P. 2924-2932
Guido Montúfar and Johannes Rauh:
Scaling of model approximation errors and expected entropy distances
In: Kybernetika,
50 (2014) 2, p. 234-245
Bibtex DOI: 10.14736/kyb-2014-2-0234 ARXIV: https://arxiv.org/abs/1207.3399Tyll Krüger ; Guido Montúfar ; Ruedi Seiler and Rainer Siegmund-Schultze:
Sequential recurrence-based multidimensional universal source coding of Lempel-Ziv
type
Bibtex MIS-Preprint: 86/2014 ARXIV: http://arxiv.org/abs/1408.4433
Repository Open AccessGuido Montúfar:
Universal approximation depth and errors of narrow belief networks with discrete units
In: Neural computation,
26 (2014) 7, p. 1386-1407
Bibtex MIS-Preprint: 74/2014 DOI: 10.1162/NECO_a_00601 ARXIV: http://arxiv.org/abs/1303.7461Guido Montúfar ; Johannes Rauh and Nihat Ay:
Maximal information divergence from statistical models defined by neural networks
In: Geometric science of information : first international conference, GSI 2013, Paris,
France, August 28-30, 2013. Proceedings / Frank Nielsen... (eds.)
Berlin [u. a.] : Springer, 2013. - P. 759-766
(Lecture notes in computer science ; 8085)
Bibtex MIS-Preprint: 31/2013 DOI: 10.1007/978-3-642-40020-9_85 ARXIV: http://arxiv.org/abs/1303.0268Guido Montúfar:
Mixture decompositions of exponential families using a decomposition of their sample
spaces
In: Kybernetika,
49 (2013) 1, p. 23-39
Bibtex MIS-Preprint: 39/2010 ARXIV: https://arxiv.org/abs/1008.0204 LINK: http://www.kybernetika.cz/content/2013/1/23Nihat Ay ; Guido Montúfar and Johannes Rauh:
Selection criteria for neuromanifolds of stochastic dynamics
In: Advances in cognitive neurodynamics III : proceedings of the 3rd International Conference
on Cognitive Neurodynamics 2011 ; [June 9-13, 2011, Hilton Niseko Village, Hokkaido,
Japan] / Yoko Yamaguchi (ed.)
Dordrecht : Springer, 2013. - P. 147-154
(Advances in cognitive neurodynamics)
Bibtex MIS-Preprint: 15/2011 DOI: 10.1007/978-94-007-4792-0_20Tyll Krüger ; Guido Montúfar ; Ruedi Seiler and Rainer Siegmund-Schultze:
Universally typical sets for ergodic sources of multidimensional data
In: Kybernetika,
49 (2013) 6, p. 868-882
Bibtex MIS-Preprint: 20/2011 ARXIV: http://arxiv.org/abs/1105.0393 LINK: http://www.kybernetika.cz/content/2013/6/868Guido Montúfar and Jason Morton:
Kernels and submodels of deep belief networks
In: NIPS 2012 : Deep learning and unsupervised feature learning workshop : [be held in
conjunction with neural information processing systems on December 8, 2012 (TBD) at
Lake Tahoe, USA]
Bibtex ARXIV: https://arxiv.org/abs/1211.0932La Jolla, CA : Neural Information Processing Systems, 2012
Guido Montúfar:
On the expressive power of discrete mixture models, restricted Boltzmann machines,
and deep belief networks - a unified mathematical treatment
Dissertation, Universität Leipzig, 2012
Bibtex LINK: http://personal-homepages.mis.mpg.de/montufar/PhDthesisGuidoMontufar.pdfGuido Montúfar and Johannes Rauh:
Scaling of model approximation errors and expected entropy distances
In: Proceedings of the 9th workshop on uncertainty processing WUPES '12 : Marianske Lazne,
Czech Republik ; 12-15th September 2012
Bibtex ARXIV: https://arxiv.org/abs/1207.3399 LINK: http://wupes.fm.vse.cz/2012/data/Wupes12_proceedings.pdfPraha : Academy of Sciences of the Czech Republik / Institute of Information Theory and Automation, 2012. - P. 137-148
Guido Montúfar and Jason Morton:
When does a mixture of products contain a product of mixtures?
In: NIPS 2012 : Deep learning and unsupervised feature learning workshop : [be held in
conjunction with neural information processing systems on December 8, 2012 (TBD) at
Lake Tahoe, USA]
Bibtex MIS-Preprint: 98/2014 ARXIV: http://arxiv.org/abs/1206.0387La Jolla, CA : Neural Information Processing Systems, 2012
Guido Montúfar ; Johannes Rauh and Nihat Ay:
Expressive power and approximation errors of restricted Boltzmann machines
In: Advances in neural information processing systems 24 : NIPS 2011 ; 25th annual conference
on neural information processing systems 2011, Granada, Spain December 12th - 15th / John Shawe-Taylor (ed.)
Bibtex MIS-Preprint: 27/2011 ARXIV: https://arxiv.org/abs/1406.3140 LINK: http://papers.nips.cc/paper/4380-expressive-power-and-approximation-errors-of-restricted-boltzmann-machines.pdfLa Jolla, CA : Neural Information Processing Systems, 2011. - P. 415-423
Guido Montúfar and Nihat Ay:
Refinements of universal approximation results for deep belief networks and restricted
Boltzmann machines
In: Neural computation,
23 (2011) 5, p. 1306-1319
Bibtex MIS-Preprint: 23/2010 DOI: 10.1162/NECO_a_00113 ARXIV: https://arxiv.org/abs/1005.1593Guido Montúfar:
Mixture models and representational power of RBM's, DBN's, and DBM's
In: NIPS 2010 : Deep learning and unsupervised feature learning workshop ; December 19,
2010, Hilton, Vancouver, Canada
Bibtex LINK: https://www.researchgate.net/publication/336197650[s. l.] : NIPS, 2010. - P. 1-9
Guido Montúfar:
Theory of transport and photon-statistics in a biased nanostructure
Diplomarbeit, Universität Berlin, 2008
Bibtex Guido Montúfar ; Marten Richter ; Tobias Brandes and Andreas Knorr:
Theory of transport and photon-statistics in a biased nanostructure
In: 2008 International Nano-Optoelectronics workshop (iNOW 2008)
Bibtex DOI: 10.1109/INOW.2008.4634528Piscataway, NJ : IEEE, 2008. - P. 243-244
Guido Montúfar:
Q-Sanov theorem for d \(\geq\) 2
Diplomarbeit, Universität Berlin, 2007
Bibtex 