Výsledky vyhledávání - exponentiated-gradient algorithm

Generalized Exponentiated Gradient Algorithms and Their Application to On-Line Portfolio Selection

Autoři: Andrzej Cichocki Sergio Cruces Auxiliadora Sarmiento a další

Přispěvatelé: Andrzej Cichocki Sergio Cruces Auxiliadora Sarmiento a další

Zdroj: idUS. Depósito de Investigación de la Universidad de Sevilla
Universidad de Sevilla (US)
IEEE Access, Vol 12, Pp 197000-197020 (2024)

Témata: FOS: Computer and information sciences, Computer Science - Machine Learning, Computer Science - Information Theory, Information Theory (cs.IT), On-line portfolio selection, on-line portfolio selection, exponentiated gradient algorithms, TK1-9971, Machine Learning (cs.LG), FOS: Economics and business, Portfolio Management (q-fin.PM), Exponentiated gradient algorithms, Alpha-beta divergences, Electrical engineering. Electronics. Nuclear engineering, Quantitative Finance - Portfolio Management

Popis souboru: application/pdf

Přístupová URL adresa: http://arxiv.org/abs/2406.00655
https://hdl.handle.net/11441/166502
https://doaj.org/article/07c770f19e6f4d1d8de43b9071d30e78

Generalized Exponentiated Gradient Algorithms Using the Euler Two-Parameter Logarithm

Autoři: Cichocki, Andrzej

Témata: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, text

URL: http://arxiv.org/abs/2502.17500

Mirror Descent and Novel Exponentiated Gradient Algorithms Using Trace-Form Entropies and Deformed Logarithms

Autoři: Cichocki, Andrzej Tanaka, Toshihisa Cruces, Sergio

Témata: FOS: Computer and information sciences, Computer Science - Machine Learning, Artificial Intelligence (cs.AI), Computer Science - Artificial Intelligence, Machine Learning (cs.LG)

Přístupová URL adresa: http://arxiv.org/abs/2503.08748

Generalized Exponentiated Gradient Algorithms and Their Application to On-Line Portfolio Selection

Autoři: Cichocki, Andrzej Cruces, Sergio Sarmiento, Auxiliadora a další

Témata: Computer Science - Machine Learning, Computer Science - Information Theory, Quantitative Finance - Portfolio Management, text

URL: http://arxiv.org/abs/2406.00655

On the Efficient Implementation of the Matrix Exponentiated Gradient Algorithm for Low-Rank Matrix Optimization

Autoři: Dan Garber Atara Kaplan

Zdroj: Mathematics of Operations Research.

Témata: FOS: Computer and information sciences, Computer Science - Machine Learning, Statistics - Machine Learning, Optimization and Control (math.OC), FOS: Mathematics, Machine Learning (stat.ML), 0101 mathematics, Mathematics - Optimization and Control, 01 natural sciences, Machine Learning (cs.LG)

Přístupová URL adresa: http://arxiv.org/abs/2012.10469

EGRank: An exponentiated gradient algorithm for sparse learning-to-rank

Autoři: Lei Du Yan Pan Jintang Ding a další

Zdroj: Information Sciences. 467:342-356

Témata: 0202 electrical engineering, electronic engineering, information engineering, 02 engineering and technology, 16. Peace & justice

Přístupová URL adresa: https://dblp.uni-trier.de/db/journals/isci/isci467.html#DuPDLH18
https://www.sciencedirect.com/science/article/pii/S0020025518305632

Convergence of exponentiated gradient algorithms

Autoři: Hill, Simon Williamson, Robert

Zdroj: IEEE Transactions on Signal Processing. 49:1208-1215

Témata: Mathematical models, 4. Education, Mean square error, Acoustic signal processing Acoustic echo cancellation, 02 engineering and technology, Echo suppression, 7. Clean energy, 3. Good health, Keywords: Algorithms, Convergence of numerical methods, Exponentiated gradient algorithms, 0202 electrical engineering, electronic engineering, information engineering, Mean squared error, Learning rate, Echo, Room acoustics, Exponentiated gradient descent

On the Efficient Implementation of the Matrix Exponentiated Gradient Algorithm for Low-Rank Matrix Optimization

Autoři: Garber, Dan Kaplan, Atara

Témata: Mathematics - Optimization and Control, Computer Science - Machine Learning, Statistics - Machine Learning, text

URL: http://arxiv.org/abs/2012.10469

A study of the Exponentiated Gradient +/- algorithm for stochastic optimization of neural networks

Autoři: Parks, David Freeman Warmuth, Manfred K1

Témata: Computer science, publication

URL: https://escholarship.org/uc/item/4ck5k544
https://escholarship.org/

A study of the Exponentiated Gradient +/- algorithm for stochastic optimization of neural networks

Autoři: Warmuth, Manfred K Parks, David Freeman

Témata: Computer science, publication

URL: https://escholarship.org/uc/item/4ck5k544
https://escholarship.org/content/qt4ck5k544/qt4ck5k544.pdf

Exponentiated gradient algorithms for conditional random fields and max-margin Markov networks

Autoři: Collins, Michael Globerson, Amir Koo, Terry a další

Přispěvatelé: Collins, Michael Globerson, Amir Koo, Terry a další

Zdroj: UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Recercat. Dipósit de la Recerca de Catalunya
instname

Témata: Àrees temàtiques de la UPC::Informàtica::Llenguatges de programació, Machine learning, Aprenentatge automàtic, Algorismes, Informàtica::Llenguatges de programació [Àrees temàtiques de la UPC]

Popis souboru: application/pdf

Přístupová URL adresa: http://hdl.handle.net/2117/9799
https://hdl.handle.net/2117/9799
https://jmlr.org/papers/v9/collins08a.html
http://www.stat.berkeley.edu/~bartlett/papers/cgkcb-egacrfmmmn-07.pdf
http://www.cs.columbia.edu/~mcollins/papers/egjournal.pdf
http://people.csail.mit.edu/mcollins/papers/egjournal.pdf
https://eprints.qut.edu.au/43998/
https://www.stat.berkeley.edu/~bartlett/papers/cgkcb-egacrfmmmn-07.pdf

Exponentiated gradient algorithms for log-linear structured prediction

Autoři: Amir Globerson Michael Collins Xavier Carreras a další

Zdroj: Proceedings of the 24th international conference on Machine learning. :305-312

Témata: 0202 electrical engineering, electronic engineering, information engineering, 02 engineering and technology, 01 natural sciences, 0105 earth and related environmental sciences

Přístupová URL adresa: http://people.csail.mit.edu/carreras/pubs/2007-icml-gkcc-2.pdf
http://people.csail.mit.edu/maestro/papers/globerson07icml.pdf
https://core.ac.uk/display/24468472
https://doi.acm.org/10.1145/1273496.1273535
https://dl.acm.org/doi/10.1145/1273496.1273535
http://www.cs.columbia.edu/~mcollins/papers/icml07.pdf
http://www.cs.upc.edu/~carreras/pubs/2007-icml-gkcc.pdf

Adaptive optimisation of composite objectives with exponentiated gradient: a family of algorithms for high-dimensional and sparse targets

Autoři: Shao, Weijia

Témata: 000 Informatik, Informationswissenschaft, allgemeine Werke::000 Informatik, Wissen, Systeme::000 Informatik, Informationswissenschaft, allgemeine Werke, 500 Naturwissenschaften und Mathematik::510 Mathematik::518 Numerische Analysis, optimisation, variance reduction, online learning, Online-Lernen, Optimierung, Adaptivität, Varianzreduktion, dimensionality, Dimensionalität, adaptivity

An analysis of the exponentiated gradient descent algorithm

Autoři: S.I. Hill Robert C. Williamson

Zdroj: ISSPA '99. Proceedings of the Fifth International Symposium on Signal Processing and its Applications (IEEE Cat. No.99EX359). 1:379-382

Témata: 0202 electrical engineering, electronic engineering, information engineering, 0102 computer and information sciences, 02 engineering and technology, 01 natural sciences

Přístupová URL adresa: http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=818191
https://ieeexplore.ieee.org/document/818191/
https://dblp.uni-trier.de/db/conf/isspa/isspa1999.html#HillW99

The binary exponentiated gradient algorithm for learning linear functions

Autoři: Tom Bylander

Zdroj: Proceedings of the tenth annual conference on Computational learning theory - COLT '97. :184-192

Témata: 0202 electrical engineering, electronic engineering, information engineering, 0102 computer and information sciences, 02 engineering and technology, 01 natural sciences

Přístupová URL adresa: https://dl.acm.org/doi/10.1145/267460.267495
http://core.ac.uk/display/22495915
https://dblp.uni-trier.de/db/conf/colt/colt1997.html#Bylander97a

On the Efficient Implementation of the Matrix Exponentiated Gradient Algorithm for Low-Rank Matrix Optimization.

Autoři: Garber, Dan Kaplan, Atara

Zdroj: Mathematics of Operations Research; Nov2023, Vol. 48 Issue 4, p2094-2128, 35p

Témata: LOW-rank matrices, SINGULAR value decomposition, QUANTUM entropy, MATRICES (Mathematics), ALGORITHMS

People: VON Neumann, John, 1903-1957

The Exponentiated Gradient Algorithms

Autoři: Constantin Paleologu Jacob Benesty Silviu Ciochină

Zdroj: Synthesis Lectures on Speech and Audio Processing ISBN: 9783031014314

Exponentiated gradient algorithms for large-margin structured classification

Autoři: Saul, L K Weiss, Y Bottou, L a další

Zdroj: Advances in Neural Information Processing Systems 17: Proceedings of the 2004 Conference

Témata: Chapter in Book, Report or Conference volume

URL: https://eprints.qut.edu.au/44012/1/eg.pdf
https://papers.nips.cc/paper/2677-exponentiated-gradient-algorithms-for-large-margin-structured-classification
https://eprints.qut.edu.au/44012/1/eg.pdf
https://papers.nips.cc/paper/2677-exponentiated-gradient-algorithms-for-large-margin-structured-classification
Bartlett, Peter, Collins, Michael, Taskar, Ben, & McAllester, David (2005) Exponentiated gradient algorithms for large-margin structured classification. In Saul, L K, Weiss, Y, & Bottou, L (Eds.) Advances in Neural Information Processing Systems 17: Proceedings of the 2004 Conference. The MIT Press, United States of America, pp. 113-120.

The Lms, Pnlms, And Exponentiated Gradient Algorithms

Autoři: Benesty, J. Huang, Yiteng

Témata: 0202 electrical engineering, electronic engineering, information engineering, 02 engineering and technology

带有自适应学习速率的矩阵指数梯度在线量子态估计算法. (Chinese)

Alternate Title: Online quantum state estimation optimization algorithm with adaptive learning rate matrix exponentiated gradient. (English)

Autoři: 丛爽 汪涛 张坤

Zdroj: Control Theory & Applications / Kongzhi Lilun Yu Yinyong; Aug2021, Vol. 38 Issue 8, p1188-1196, 9p

Témata: DENSITY matrices, QUANTUM entropy, RANDOM noise theory, ALGORITHMS, MATHEMATICAL optimization, QUBITS

People: VON Neumann, John, 1903-1957