Access the full text.
Sign up today, get DeepDyve free for 14 days.
Aleix Martinez (2002)
Recognizing Imprecisely Localized, Partially Occluded, and Expression Variant Faces from a Single Sample per ClassIEEE Trans. Pattern Anal. Mach. Intell., 24
K. Crammer, Michael Kearns, Jennifer Vaughan (2006)
Learning from Multiple SourcesJ. Mach. Learn. Res., 9
Judy Hoffman, Eric Tzeng, Trevor Darrell, Kate Saenko (2015)
Simultaneous Deep Transfer Across Domains and Tasks2015 IEEE International Conference on Computer Vision (ICCV)
Kate Saenko, B. Kulis, Mario Fritz, Trevor Darrell (2010)
Adapting Visual Category Models to New Domains
Corinna Cortes, M. Mohri, Andrés Medina (2014)
Adaptation Algorithm and Theory Based on Generalized DiscrepancyProceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
Krikamol Muandet, D. Balduzzi, B. Scholkopf (2013)
Domain Generalization via Invariant Feature RepresentationArXiv, abs/1301.2115
Sinno Pan, Xiaochuan Ni, Jian-Tao Sun, Qiang Yang, Zheng Chen (2010)
Cross-domain sentiment classification via spectral feature alignment
C. Arndt (2001)
Information Measures: Information and its Description in Science and Engineering
Mingsheng Long, Yue Cao, Jianmin Wang, Michael Jordan (2015)
Learning Transferable Features with Deep Adaptation NetworksArXiv, abs/1502.02791
Judy Hoffman, E. Rodner, Jeff Donahue, Kate Saenko, Trevor Darrell (2013)
Efficient Learning of Domain-invariant Image RepresentationsCoRR, abs/1301.3224
A. Rényi (1961)
On Measures of Entropy and Information
Judy Hoffman, B. Kulis, Trevor Darrell, Kate Saenko (2012)
Discovering Latent Domains for Multisource Domain Adaptation
(1972)
Applications and Extensions of an Algorithm That Computes Fixed Points of Certain Upper Semi-continuous Point to Set Mappings
Yuhai Wu (2021)
Statistical Learning TheoryTechnometrics, 41
L. Brouwer (1910)
Über eineindeutige, stetige Transformationen von Flächen in sichMathematische Annalen, 79
B. Eaves (1972)
Homotopies for computation of fixed pointsMathematical Programming, 3
Shai Ben-David, John Blitzer, K. Crammer, Fernando Pereira (2006)
Analysis of Representations for Domain Adaptation
Yaroslav Ganin, V. Lempitsky (2014)
Unsupervised Domain Adaptation by Backpropagation
Boqing Gong, Yuan Shi, Fei Sha, K. Grauman (2012)
Geodesic flow kernel for unsupervised domain adaptation2012 IEEE Conference on Computer Vision and Pattern Recognition
Mark Dredze, K. Crammer, Fernando Pereira (2008)
Confidence-weighted linear classification
This article has been accepted for inclusion in a future issue of this journal. Content is final as presented, with the exception of pagination. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 1 Domain Adaptation from Multiple Sources: A Domain-
Jun Deng, Zixing Zhang, F. Eyben, Björn Schuller (2014)
Autoencoder-based Unsupervised Domain Adaptation for Speech Emotion RecognitionIEEE Signal Processing Letters, 21
Y. Mansour, M. Mohri, Afshin Rostamizadeh (2009)
Domain Adaptation: Learning Bounds and AlgorithmsArXiv, abs/0902.3430
M. Hirsch, C. Papadimitriou, S. Vavasis (1987)
Exponential lower bounds for finding Brouwer fixed points28th Annual Symposium on Foundations of Computer Science (sfcs 1987)
F. Seide, Gang Li, Xie Chen, Dong Yu (2011)
Feature engineering in Context-Dependent Deep Neural Networks for conversational speech transcription2011 IEEE Workshop on Automatic Speech Recognition & Understanding
Zhongyi Pei, Zhangjie Cao, Mingsheng Long, Jianmin Wang (2018)
Multi-Adversarial Domain AdaptationArXiv, abs/1809.02176
Jeff Donahue, Yangqing Jia, Oriol Vinyals, Judy Hoffman, Ning Zhang, Eric Tzeng, Trevor Darrell (2013)
DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
Maite Taboada, Julian Brooke, Milan Tofiloski, Kimberly Voll, Manfred Stede (2011)
Lexicon-Based Methods for Sentiment AnalysisComputational Linguistics, 37
Jing Jiang, ChengXiang Zhai (2007)
Instance Weighting for Domain Adaptation in NLP
Zheng Xu, Wen Li, Li Niu, Dong Xu (2014)
Exploiting Low-Rank Structure from Latent Domains for Domain Generalization
Y. Mansour, M. Mohri, Afshin Rostamizadeh (2009)
Multiple Source Adaptation and the Rényi DivergenceArXiv, abs/1205.2628
J. Neumann (1928)
Zur Theorie der GesellschaftsspieleMathematische Annalen, 100
Lixin Duan, I. Tsang, Dong Xu, Tat-Seng Chua (2009)
Domain adaptation from multiple sources via auxiliary classifiers
T. Dinh, Hoai Thi (1997)
Convex analysis approach to d.c. programming: Theory, Algorithm and Applications, 22
Corinna Cortes, M. Mohri (2014)
Domain adaptation and sample bias correction theory and algorithm for regressionTheor. Comput. Sci., 519
Jiayuan Huang, Alex Smola, A. Gretton, K. Borgwardt, B. Scholkopf (2006)
Correcting Sample Selection Bias by Unlabeled Data
John Blitzer, Mark Dredze, Fernando Pereira (2007)
Biographies, Bollywood, Boom-boxes and Blenders: Domain Adaptation for Sentiment Classification
W. Gander, U. Matt (1998)
A D.C. OPTIMIZATION ALGORITHM FOR SOLVING THE TRUST-REGION SUBPROBLEM∗
Lei Zhang, B. Liu (2012)
Sentiment Analysis and Opinion Mining
Judy Hoffman, M. Mohri, Ningshan Zhang (2018)
Algorithms and Theory for Multiple-Source AdaptationArXiv, abs/1805.08727
Boqing Gong, K. Grauman, Fei Sha (2013)
Connecting the Dots with Landmarks: Discriminatively Learning Domain-Invariant Features for Unsupervised Domain Adaptation
Harold Kuhn (1968)
Simplicial approximation of fixed points.Proceedings of the National Academy of Sciences of the United States of America, 61 4
Kun Zhang, Mingming Gong, B. Scholkopf (2015)
Multi-Source Domain Adaptation: A Causal View
Raghuraman Gopalan, Ruonan Li, R. Chellappa (2011)
Domain adaptation for object recognition: An unsupervised approach2011 International Conference on Computer Vision
T. Cover, Joy Thomas (1991)
Elements of Information Theory
Y. Mansour, M. Mohri, Afshin Rostamizadeh (2008)
Domain Adaptation with Multiple Sources
Hal Daumé (2007)
Frustratingly Easy Domain AdaptationArXiv, abs/0907.1815
A. Yuille, Anand Rangarajan (2003)
The Concave-Convex ProcedureNeural Computation, 15
G. Blanchard, Gyemin Lee, C. Scott (2011)
Generalizing from Several Related Classification Tasks to a New Unlabeled Sample
Brian Roark, R. Sproat, Cyril Allauzen, M. Riley, Jeffrey Sorensen, Terry Tai (2012)
The OpenGrm open-source finite-state grammar software libraries
Bharath Sriperumbudur, Gert Lanckriet (2012)
A Proof of Convergence of the Concave-Convex Procedure Using Zangwill's TheoryNeural Computation, 24
Corinna Cortes, Spencer Greenberg, M. Mohri (2013)
Relative deviation learning bounds and generalization with unbounded loss functionsAnnals of Mathematics and Artificial Intelligence, 85
Ross Girshick, Jeff Donahue, Trevor Darrell, J. Malik (2013)
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014 IEEE Conference on Computer Vision and Pattern Recognition
H. Scarf (1967)
The Approximation of Fixed Points of a Continuous MappingSiam Journal on Applied Mathematics, 15
Xavier Glorot, Antoine Bordes, Yoshua Bengio (2011)
Domain Adaptation for Large-Scale Sentiment Classification: A Deep Learning Approach
Eric Tzeng, Judy Hoffman, Kate Saenko, Trevor Darrell (2017)
Adversarial Discriminative Domain Adaptation2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
T. Erven, P. Harremoës (2012)
Rényi Divergence and Kullback-Leibler DivergenceIEEE Transactions on Information Theory, 60
T. Dinh, Hoai Thi (1998)
A D.C. Optimization Algorithm for Solving the Trust-Region SubproblemSIAM J. Optim., 8
H. Liao (2013)
Speaker adaptation of context dependent deep neural networks2013 IEEE International Conference on Acoustics, Speech and Signal Processing
A. Khosla, Tinghui Zhou, Tomasz Malisiewicz, Alexei Efros, A. Torralba (2012)
Undoing the Damage of Dataset Bias
Jun Yang, Rong Yan, Alexander Hauptmann (2007)
Cross-domain video concept detection using adaptive svmsProceedings of the 15th ACM international conference on Multimedia
R. Horst, N. Thoai (1999)
DC Programming: OverviewJournal of Optimization Theory and Applications, 103
Boqing Gong, K. Grauman, Fei Sha (2013)
Reshaping Visual Datasets for Domain Adaptation
Yaniv Taigman, A. Polyak, Lior Wolf (2016)
Unsupervised Cross-Domain Image GenerationArXiv, abs/1611.02200
A. Torralba, Alexei Efros (2011)
Unbiased look at dataset biasCVPR 2011
David Editor
Artificial Intelligence and Language Processing a Theory of the Learnable
Xi Chen, Xiaotie Deng (2008)
Matching algorithmic bounds for finding a Brouwer fixed pointJ. ACM, 55
A. Krizhevsky, Ilya Sutskever, Geoffrey Hinton (2012)
ImageNet classification with deep convolutional neural networksCommunications of the ACM, 60
Alison Gibbs, F. Su (2002)
On Choosing and Bounding Probability MetricsInternational Statistical Review, 70
Publisher's note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations
We present a general theoretical and algorithmic analysis of the problem of multiple-source adaptation, a key learning problem in applications. We derive new normalized solutions with strong theoretical guarantees for the cross-entropy loss and other similar losses. We also provide new guarantees that hold in the case where the conditional probabilities for the source domains are distinct. We further present a novel analysis of the convergence properties of density estimation used in distribution-weighted combinations, and study their effects on the learning guarantees. Moreover, we give new algorithms for determining the distribution-weighted combination solution for the cross-entropy loss and other losses. We report the results of a series of experiments with real-world datasets. We find that our algorithm outperforms competing approaches by producing a single robust predictor that performs well on any target mixture distribution. Altogether, our theory, algorithms, and empirical results provide a full solution for the multiple-source adaptation problem with very practical benefits.
Annals of Mathematics and Artificial Intelligence – Springer Journals
Published: Nov 5, 2020
Read and print from thousands of top scholarly journals.
Already have an account? Log in
Bookmark this article. You can see your Bookmarks on your DeepDyve Library.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Copy and paste the desired citation format or use the link below to download a file formatted for EndNote
Access the full text.
Sign up today, get DeepDyve free for 14 days.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.