Journal Publications

 
Adaptive Subgradient Methods for Online Learning and Stochastic Optimization
Duchi, E. Hazan, Y. Singer
Journal of Machine Learning Research, to appear.

Pegasos: Primal Estimated sub-GrAdient SOlver for SVM
S. Shalev-Shwartz, Y. Singer, N. Srebro, A. Cotter
Mathematical Programming, to appear.

On the Equivalence of Weak Learnability and Linear Separability:
New Relaxations and Efficient Boosting Algorithms
S. Shalev-Shwartz and Y. Singer
Machine Learning, Vol. 80(2/3), pp. 141-163, 2010.

Online and Batch Learning using Forward-Backward Splitting
J. Duchi and Y. Singer
Journal of Machine Learning Research, Vol. 10, pp. 2899-2934, 2009.

Individual Sequence Prediction using Memory-efficient Context Trees
O. Dekel, S. Shalev-Shwartz, Y. Singer
IEEE Transactions on Information Theory, Vol. 55(11), pp. 5251-5262, Nov. 2009.

Online Learning of Complex Prediction Problems Using Simultaneous Projections
Y. Amit, S. Shalev-Shwartz, Y. Singer
Journal of Machine Learning Research, Vol. 9, pp. 1399-1435, Jul. 2008. 

The Forgetron: A Kernel-Based Perceptron on a Budget
O. Dekel, S. Shalev-Shwartz, Y. Singer
SIAM Journal of Computing, Vol. 37, Issue 5, Pages 1342-1372, 2008.

A Primal-Dual Perspective of Online Learning Algorithms
S. Shalev-Shwartz and Y. Singer
Machine Learning Journal, 69:2/3, pages 115 - 142, 2007.

Online Learning of Multiple Tasks with a Shared Loss
O. Dekel, P.M. Long, Y. Singer
Journal of Machine Learning Research, Vol. 8, pp. 2233-2264, 2007.

A Large Margin Algorithm for Speech-to-Phoneme and Music-to-Score Alignment
J. Keshet, S. Shalev-Shwartz, Y. Singer, D. Chazan
IEEE Transactions on Audio, Speech and Language Processing, Vol. 15(8), 
pp. 2373-2382, Nov. 2007. 

Efficient Learning of Label Ranking by Soft Projections onto Polyhedra
S. Shalev-Shwartz and Y. Singer
Journal of Machine Learning Research, Vol. 7, pp. 1567-1599, July 2006.
Code of the algorithm described in the paper

Online Passive-Aggressive Algorithms
K. Crammer, O. Dekel, J. Keshet, S. Shalev-Shwartz, Y. Singer
Journal of Machine Learning Research Vol. 7, pp. 551-585, 2006.

Smooth Epsilon-Insensitive Regression by Loss Symmetrization
O. Dekel, S. Shalev-Shwartz, Y. Singer
Journal of Machine Learning Research, Vol. 6, pp. 711-741, May 2005.

Spikernels: Embedding Spiking Neurons in Inner-Product Spaces
L. Shpigelman, Y. Singer, R. Paz, E. Vaadia
Neural Computation, Vol. 17(3), pp. 671-690, 2005.

Online Ranking by Projecting
K. Crammer and Y. Singer,
Neural Computation, Vol. 17(1), pp. 145-175, Jan. 2005. 

Efficient boosting algorithms for combining preferences
Y. Freund, Raj Iyer, R.E. Schapire, Y. Singer,
Journal of Machine Learning Research, Vol. 4, pp. 933-969, Nov. 2003.

A Family of Additive Online Algorithms for Category Ranking
K. Crammer and Y. Singer
Journal of Machine Learning Research, Vol. 3, pp. 1025-1058, Feb. 2003.

Ultraconservative Online Algorithms for Multiclass Problems
K. Crammer and Y. Singer
Journal of Machine Learning Research, Vol. 3, pp. 951-991, Jan. 2003.

Protein Family Classification using Sparse Markov Transducers
E. Eskin, W. Noble, Y. Singer
Journal of Computational Biology, Vol. 10(2), pp. 187-214, 2003.

Using substitution matrices to estimate probability distributions for biological sequences
E. Eskin, W. Grundy, Y. Singer
Journal of Computational Biology. Vol. 2(6), pp. 775-792, 2002. 

Logistic Regression, AdaBoost and Bregman Distances
M. Collins, R. Schapire, Y. Singer
Machine Learning, Vol. 48(1/3), pp. 253-285, 2002.

On the Learnability and Design of Output Codes for Multiclass Problems
K. Crammer and Y. Singer
Machine Learning, Vol. 47(2/3), pp. 201-233, 2002.

On the Algorithmic Implementation o Multiclass Kernel-based Vector Machines
K. Crammer and Y. Singer
Journal of Machine Learning Research, Vol. 2, pp. 265-292, 2001.

Reducing Multiclass to Binary: A Unifying Approach for Margin Classifiers
E. Allwein, R. Schapire, Y. Singer
Journal of Machine Learning Research, Vol. 1, pp. 113-141, 2000.

BoosTexter: A Boosting-based System for Text Categorization
R.E. Schapire and Y. Singer
Machine Learning, Vol. 39(2/3), pp. 135-168, 2000.

Improved Boosting Algorithms using Confidence-rated Predictions
R.E. Schapire and Y. Singer
Machine Learning, Vol. 37(3), pp. 1-40, 1999.

An Efficient Extension to Mixture Techniques for Prediction and Decision Trees
F.C. Pereira and Y. Singer
Machine Learning, Vol. 36(3), pp. 183-199, 1999.

Learning to Order Things
W.W. Cohen, R.E. Schapire, Y. Singer
Journal of Artificial Intelligence Research, Vol. 10, pp. 243-270, 1999.

Context-sensitive Learning Methods for Text Categorization
W.W. Cohen and Y. Singer
ACM Transactions on Information Systems, Vol. 17(2), pp. 1-33, 1999.

Switching Portfolios
Y. Singer
International Journal of Neural Systems, Vol. 8(4), pp. 445-456, 1998.

On-line Portfolio Selection using Multiplicative Updates
D.P. Helmbold, R.E. Schapire, Y. Singer,  M.K. Warmuth
Mathematical Finance, Vol. 8(4), pp. 325-347, 1998.

On the Learnability and Usage of Acyclic Probabilistic Finite Automata
D. Ron, Y. Singer, N. Tishby
Journal of Computer and System Sciences, 56(2), pp. 133-152, 1998.

The Hierarchical Hidden Markov Model: analysis and applications
S. Fine, Y. Singer, N. Tishby,
Machine Learning, Vol. 32(1), pp. 41-62, 1998.

Adaptive Mixtures of Probabilistic Transducers
Y. Singer
Neural Computation, Vol. 9(8), pp. 1711-1734, 1997.

A comparison of new and old algorithms for a mixture estimation problem
D.P. Helmbold, R.E. Schapire, Y. Singer, M.K. Warmuth
Machine Learning, Vol. 27(1), pp. 97-119, 1997.

The power of amnesia: learning probabilistic automata with variable memory length
D. Ron, Y. Singer, N. Tishby
Machine Learning, Vol. 25(2), pp. 117-150, 1996.

Dynamical encoding of cursive handwriting
Y. Singer and N. Tishby
Biological Cybernetics, Vol. 71(3), pp. 227-237, 1994.
http://www.magicbroom.info/Papers/DuchiHaSi10.pdfhttp://www.magicbroom.info/Papers/ShalevSiSrCo09.pdfhttp://www.magicbroom.info/Papers/ShalevSi10.pdfhttp://www.magicbroom.info/Papers/ShalevSi10.pdfhttp://jmlr.csail.mit.edu/papers/volume10/duchi09a/duchi09a.pdfhttp://www.magicbroom.info/Papers/DekelShSi09.pdfhttp://www.magicbroom.info/Papers/AmitShSi08.pdfhttp://www.magicbroom.info/Papers/DekelShSi08.pdfhttp://www.springerlink.com/content/h2374415m4nw31x0/fulltext.pdfhttp://www.jmlr.org/papers/volume8/dekel07a/dekel07a.pdfhttp://www.magicbroom.info/Papers/KeshetShSiCh07.pdfhttp://jmlr.csail.mit.edu/papers/volume7/shalev-shwartz06a/shalev-shwartz06a.pdfhttp://jmlr.csail.mit.edu/papers/volume7/shalev-shwartz06a/shalev-shwartz06a_code.tgzhttp://jmlr.csail.mit.edu/papers/volume7/crammer06a/crammer06a.pdfhttp://www.magicbroom.info/Papers/ShalevSi07.pdfhttp://www.magicbroom.info/Papers/ShalevSi07.pdfhttp://www.magicbroom.info/Papers/ShalevSi07.pdfhttp://jmlr.csail.mit.edu/papers/volume4/freund03a/freund03a.pdfhttp://www.magicbroom.info/Papers/ShalevSi07.pdfhttp://www.magicbroom.info/Papers/ShalevSi07.pdfhttp://www.magicbroom.info/Papers/ShalevSi07.pdfhttp://www.magicbroom.info/Papers/ShalevSi07.pdfhttp://www.magicbroom.info/Papers/ShalevSi07.pdfhttp://www.magicbroom.info/Papers/ShalevSi07.pdfhttp://jmlr.csail.mit.edu/papers/volume2/crammer01a/crammer01a.pdfhttp://www.magicbroom.info/Papers/ShalevSi07.pdfhttp://www.magicbroom.info/Papers/ShalevSi07.pdfhttp://www.springerlink.com/content/k8h6104h15144610/fulltext.pdfhttp://www.springerlink.com/content/m36100k56417v157/fulltext.pdfhttp://www.springerlink.com/content/h7630r4u78j0xhu1/fulltext.pdfhttp://www.springerlink.com/content/p158331038351812/fulltext.pdfhttp://www.springerlink.com/content/p158331038351812/fulltext.pdfhttp://www.magicbroom.info/Papers/SingerTi94.pdfshapeimage_2_link_0shapeimage_2_link_1shapeimage_2_link_2shapeimage_2_link_3shapeimage_2_link_4shapeimage_2_link_5shapeimage_2_link_6shapeimage_2_link_7shapeimage_2_link_8shapeimage_2_link_9shapeimage_2_link_10shapeimage_2_link_11shapeimage_2_link_12shapeimage_2_link_13shapeimage_2_link_14shapeimage_2_link_15shapeimage_2_link_16shapeimage_2_link_17shapeimage_2_link_18shapeimage_2_link_19shapeimage_2_link_20shapeimage_2_link_21shapeimage_2_link_22shapeimage_2_link_23shapeimage_2_link_24shapeimage_2_link_25shapeimage_2_link_26shapeimage_2_link_27shapeimage_2_link_28shapeimage_2_link_29shapeimage_2_link_30shapeimage_2_link_31shapeimage_2_link_32