PAPERS
When it is appropriate, I organize my research perspective on certain themes into a
monograph. Here are two books that have resulted.
The Informational Complexity of Learning: Perspectives on Neural Networks and Generative Grammar
Kluwer Academic Publishers , 1998.
The Computational Nature of Language Learning and Evolution
MIT Press , 2006.
Here are my other publications partially sorted by area.
Some of them are downloadable.
STATISTICAL INFERENCE, MACHINE LEARNING,
AND INFORMATION EXTRACTION
Theory: Analyses and Algorithms
- Convergence of Laplacian Eigenmaps.
M. Belkin and P. Niyogi
Preprint
[pdf]
- A Topological View of Unsupervised Learning and Clustering.
P. Niyogi, S. Smale, and S. Weinberger
Preprint
[pdf]
- Sampling Hypersurfaces through Diffusion
H. Narayanan and P. Niyogi
Proc. of 12th Intl. Workshop on Randomization and Computation
(RANDOM) August, 2008
[pdf]
- Manifold Regularization and Semi-supervised Learning: Some
Theoretical Analyses.
P. Niyogi
Technical Report TR-2008-01, Computer Science Dept., University
of Chicago, 2008
[pdf]
- On the Relation between Low Density Separation, Spectral Clustering,
and Graph Cuts.
H. Narayanan, M. Belkin, and P. Niyogi
Proc. of Neural Information Processing Systems (NIPS), 2006
[pdf]
[appendix]
- Towards a Theoretical Foundation for Laplacian Based Manifold
Methods.
M. Belkin and P. Niyogi
to appear, Journal of Computer and System Sciences, 2007.
[pdf]
- Finding the Homology of Submanifolds with High Confidence
from Random Samples.
P. Niyogi, S. Smale, and S. Weinberger
to appear, Discrete and Computational Geometry, 2006.
[pdf]
- Mercer's Theorem, Feature Maps, and Smoothing.
Ha Quang Minh, P. Niyogi, and Y. Yao
Proc. of Computational Learning Theory (COLT), 2006.
[pdf]
- Heat flow and a Faster Algorithm to Compute
the Surface Volume of a Convex Body.
M. Belkin, H. Narayanan, and P. Niyogi
IEEE Conference on Foundations of Computer Science
(FOCS), October, 2006.
[pdf]
- Laplacian Score for Feature Selection.
X. He, Deng Cai, and P. Niyogi
Proc. of Neural Information Processing Systems, Dec. 2005.
[pdf]
- Tensor Subspace Analysis.
X. He, Deng Cai, and P. Niyogi
Proc. of Neural Information Processing Systems, Dec. 2005.
[pdf]
- Beyond the Point Cloud: From Transductive to Semisupervised Learning.
V. Sindhwani, P. Niyogi, and M. Belkin
Proc. of International Conference on Machine Learning, 2005.
[pdf]
- The Geometric Basis of Semi-supervised Learning.
V. Sindhwani, M. Belkin, and P. Niyogi
Book Chapter in Semi-supervised Learning, (Chapelle, Schoelkopf, Zien: editors)
MIT Press, 2006.
[pdf]
- Stability and Generalization of Bipartite Ranking Algorithms.
S. Agarwal and P. Niyogi
Proc. of Computational Learning Theory, 2005.
[pdf]
- On Manifold Regularization.
M. Belkin, P. Niyogi, and V. Sindhwani
Proc. of Conference on AI and Statistics, 2005.
[pdf]
- Towards a Theoretical Foundation for Laplacian-Based Manifold Methods.
M. Belkin and P. Niyogi
Proc. of Computational Learning Theory, 2005.
[pdf]
- Manifold Regularization: a Geometric Framework for Learning from
Examples.
M. Belkin, V. Sindhwani, and P. Niyogi
University of Chicago CS Tech. Report ,
TR-2004-06, 2004.
Journal of Machine Learning Research) Vol 7:2399-2434, 2006.
[pdf]
- Laplacian Eigenmaps for Dimensionality Reduction and
Data Representation.
M. Belkin and P. Niyogi
Neural Computation ,
15 (6):1373-1396, June 2003.
[pdf]
- Regularization and Regression
on Large Graphs.
M. Belkin, I. Matveeva, P. Niyogi.
Proc. of Computational Learning Theory, Banff, Canada. 2004.
[pdf]
- Face Recognition
Using Laplacianfaces.
X. He, S. Yan, Y. Hu, P. Niyogi, H-J. Zhang.
IEEE Transactions on Pattern Analysis and Machine Intelligence ,
Vol. 27, No. 3, Mar. 2005.
[pdf]
-
General Conditions for Predictivity in Learning Theory.
T. Poggio, R. Rifkin, S. Mukherjee, P. Niyogi.
Nature , Vol. 428, 419-422, 2004.
[pdf]
-
Learning Theory: Stability is Sufficient for Generalization
and Necessary and Sufficient for Empirical Risk Minimization.
S. Mukherjee, P. Niyogi, T. Poggio, R. Rifkin.
Advances in Computational Mathematics , Vol. 25, Nos. 1-3, July 2006.
[pdf]
- Almost-everywhere algorithmic
stability and generalization error.
S. Kutin and P. Niyogi.
Proc. of Uncertainty in AI, Edmonton, Canada. 2002.
[ps] (for longer technical report
version, see below.)
- Almost-everywhere algorithmic stability and generalization error.
S. Kutin and P. Niyogi.
Tech. Report TR-2002-03, Univ. of Chicago, Computer Science Department, 2002.
[ps]
- The interaction of stability and weakness in Adaboost.
S. Kutin and P. Niyogi.
Tech. Report TR-2001-30, Univ. of Chicago, Computer Science
Department, 2001.
[ps]
- Semi-supervised learning on Riemannian
manifolds.
M. Belkin and P. Niyogi.
Machine Learning Journal. Vol. 56, pp. 209-239, 2004.
[pdf]
(also, Tech. Report TR-2002-12,
Univ. of Chicago, Computer Science Dept.
[ps]
- Using manifold structure for partially labelled classification
M. Belkin and P. Niyogi.
Proc. of Advances in Neural Information Processing Systems,
vol. 15, 2003. (presented, Dec. 2002).
[pdf]
- Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering.
M. Belkin and P. Niyogi.
Proceedings of Advances in Neural Information Processing Systems.
Vol. 14, 2002. (presented, Dec. 2001).
[pdf]
-
Locality Preserving Projections.
Xiaofei He and Partha Niyogi.
Tech Report TR-2002-09, Univ. of Chicago, Computer Science Department.
2002.
[ps]
- An Approach to Data Reduction
and Clustering with Theoretical Guarantees.
P. Niyogi and N. K. Karmarkar.
Proc. of International Conference on Machine Learning
(ICML-2000). Stanford, CA, July, 2000.
[pdf]
- Generalization Error Bounds for
for Function Approximation from Scattered Noisy Data.
P. Niyogi and F. Girosi.
Advances in Computational Mathematics , Vol. 10, No. 1, 1999.
[ps]
-
Incorporating Prior Knowledge in Machine Learning by Creating Virtual Examples.
P. Niyogi, F. Girosi, and T. Poggio.
Proceedings of IEEE, Vol. 86.11, 1998.
[ps]
- On the Relationship between
Generalization Error, Hypothesis Complexity and Sample Complexity in
Regularization Networks.
P. Niyogi and F. Girosi.
Neural Computation, Vol. 8.4, 1996.
(Version of MIT AI Memo-1467, 1994.
[ps])
- Free to Choose: Investigating the Sample Complexity
for Active Learning of Real Valued Functions.
P. Niyogi.
Proc. of International Conference on Machine Learning
(ICML-95). Lake Tahoe, CA, July, 1995.
(The conference paper is missing from my archives. For a longer
version of this paper, see below)
- Sequential Optimal Recovery: A Paradigm for
Active Learning.
P. Niyogi.
AI Memo-1514. Massachussetts Institute of Technology. 1995.
[ps]
(This may also be downloadable from MIT.)
- Approximation and Estimation Bounds
for Radial Basis Function Networks.
P. Niyogi and F. Girosi.
Proc. of IMACS World Congress on Computation and Applied Mathematics.
Atlanta, Georgia, July 1994. (superseded by journal versions above.)
-
An Active Learning Formulation for Function
Approximation.
K. K. Sung and P. Niyogi.
Proc. of Advances in Neural Information Processings Systems.
Vol. 7, San Mateo, CA, 1995.
Download
- Perspectives from the Informational Complexity of
Learning.
P. Niyogi.
Proceedings of International Conference of Circuits and Systems
,Geneva, Switzerland, May, 2000.
[ps]
-
Multiple Classifiers by Constrained Minimization.
P. Niyogi, J. B. Pierrot, and O. Siohan.
Proc. of the International Conference on Acoustics, Speech,
and Signal Processing, Istanbul, Turkey, June, 2000.
[pdf]
-
An Active Learning Formulation with Applications to Object Detection.
K. K. Sung and P. Niyogi.
submitted to International Journal of Pattern Recognition and AI.
(Version of MIT AI Memo-1483).
(This paper never appeared due to the unfortunate and sudden demise
of Kah Kay Sung.)
- Epsilon Focusing -- A Strategy for
Active Example Selection.
P. Niyogi and K. K. Sung.
Knowledge Based Systems Journal, Vol. 10.7, 1998.
-
Choosing RBF Centers with the Support Vector
Algorithm.
C. Burges, F. Girosi, P. Niyogi, T. Poggio, B. Scholkopt,
K. Sung, and V. Vapnik.
IEEE Transactions in Signal Processing, Vol. 45,
No. 11, Nov., 1997. (Version of MIT AI Memo-1599).
-
Active Learning the Weights of an RBF Network.
K. K. Sung and P. Niyogi.
Proc. of IEEE--Neural Networks and Signal Processing Conference
, September, 1995, Boston. Download
- Epsilon Focusing -- A Strategy for
Active Example Selection.
P. Niyogi and K.K.Sung.
Pacific Asia Conference on Knowledge Discover and Data Mining
, Singapore, Feb. 1997.
THE HUMAN LANGUAGE SYSTEM
Language Acquisition
-
Comment on Multiple Solutions..(by B. Macwhinney).,
P. Niyogi
Journal of Child Language , vol. 31, 2004.
[pdf]
-
Optimizing the Mutual Intelligibility of Linguistic Agents
in a Shared World,
N. Komarova and P. Niyogi.
Artificial Intelligence Journal , vol. 154, pp. 1-42, 2004.
[pdf]
- Learning From Triggers.
P. Niyogi and R. C. Berwick.
Linguistic Inquiry, Vol. 28.1, 1996.
-
A Language Learning Model for Finite Parameter Spaces.
P. Niyogi and R. C. Berwick.
Cognition , Vol. 61, pp. 161-193, 1996.
- Formal Models for Learning Finite
Parameter Spaces.
P. Niyogi and R. C. Berwick.
Workshop on Cognitive Models for Language Acquisition ,
April 1994, Tilburg University, The Netherlands.
- Formal Models for Learning
in the Principles and Parameters Framework.
P. Niyogi and R. C. Berwick.
book chapter in Models of Language Learning: Inductive and Deductive Approaches ed: Peter Broeder and Jaap Murre, Oxford University Press, 2000.
-
A Markov Language Learning Model for Finite Parameter Spaces.
P. Niyogi and R. C. Berwick.
Proc. of the Annual Conference of the Association for
Computational Linguistics, New Mexico, July 1994.
Language Evolution
- Quantifying the Functional Load of Phonemic
Oppositions, Distinctive Features, and Suprasegmentals.
D. Surendran and P. Niyogi
Book Chapter in Competing Models of Language Change: Evolution and Beyond,
(O. Nedergaard Thomsen, editor)
John Benjamins, 2006.
[pdf]
- Phase Transitions in Language Evolution.
P. Niyogi.
Book Chapter in Variation and Universals in Biolinguistics,
(L. Jenkins, editor)
North Holland Linguistics Series 62, Elsevier Press,
2004.
[pdf]
-
Computational and Evolutionary Aspects of Language.
M. Nowak, N. Komarova, P. Niyogi.
Nature, Vol. 417, pp. 611-617, 2002.
[pdf]
- The Computational Study of Diachronic Linguistics.
P. Niyogi.
Diachronic Generative Syntax VI, 2000.
[pdf]
- The Computational Study of Diachronic Linguistics.
P. Niyogi.
Book Chapter in Syntactic Effects of Morphological Change (D.
Lightfoot, editor)
Cambridge University Press, 2002. (same as above).
[ps]
-
The Evolutionary Dynamics of Grammar Acquisition.
Komarova, N. L., Niyogi, P. and Nowak, M. A.
J. Theor. Biology, 209(1), pp. 43-59. 2001.
[pdf]
-
Evolution of universal grammar.
Martin A. Nowak, Natalia Komarova, and Partha Niyogi.
Science, 291:114-118, 2001.
[pdf]
- Models of Cultural Evolution and their Application
to Language Change.
P. Niyogi.
Book Chapter in Language Evolution through Language Acquisition,
(E. J. Briscoe, editor)
Cambridge University Press, 2000.
[ps]
-
Modeling the Dynamics of Historical Linguistics.
P. Niyogi.
New England Conference on Complex Systems, Sept. 1997, Nashua, NH.
- Evolutionary Consequences of
Language Learning.
P. Niyogi and R. C. Berwick.
Journal of Linguistics and Philosophy,
Vol. 17, 1997.
[pdf]
- A Dynamical Systems Model for
Language Change.
P. Niyogi and R. C. Berwick.
Complex Systems, Vol. 11., pp. 161-204, 1997.
[ps]
-
The Logical Problem of Language
Change: A Case Study of European Portuguese.
P. Niyogi and R. C. Berwick.
Syntax: A Journal
of Theoretical, Experimental, and Interdisciplinary Research, Vol. 1,
1998.
[ps]
-
Populations of Learners: The Case of European Portuguese.
P. Niyogi and R. C. Berwick.
Proc. of the Nineteenth Annual Meeting of the Cognitive
Science Society, August, 1997, Stanford, CA.
[ps]
-
Explaining Language Change: Complex Consequences of
Simple Learning Algorithms.
P. Niyogi.
AAAI Fall symposium on
Complex Behaviors, Nov. 9-11, 1996, MIT, Cambridge, MA.
- Dynamical Systems for Language
Change in Parametric Grammars.
P. Niyogi and R. C. Berwick.
Conference on Mathematics of Language, October, 1995,
University of Pennsylvania.
- Formal Models of Parameter Acquisition and Associated
Models of Parameter Change.
P. Niyogi.
Workshop on Formal Models of Language Learnability
, May 15-17, 1995, University of Maryland.
- The Logical Problem of Language
Change.
P. Niyogi and R. C. Berwick.
AI Memo-1516, MIT, July, 1995.
[ps]
Speech Recognition and Perception
- A Probabilistic Speech Recognition Framework Based on
the Temporal Dynamics of Distinctive Feature Landmark Detectors.
A. Jansen and P. Niyogi
Tech. Report, TR-2007-07, Computer Science Dept., University
of Chicago, 2007.
[pdf]
- Semisupervised Learning of Speech Sounds.
A. Jansen and P. Niyogi
Proceedings of Interspeech,2006.
[pdf]
- Intrinsic Fourier Analysis on the Manifold of Speech Sounds.
A. Jansen and P. Niyogi
Proceedings of the International Conference on Acoustics, Speech,
and Signal Processing,
Toulose, France, 2006.
[pdf]
- Robust Acoustic Based Syllable Detection.
Z. Xie and P. Niyogi
Proceedings of Interspeech,, 2006.
[pdf]
- A Geometric Perspective on Speech Sounds.
A. Jansen and P. Niyogi
Tech. Report TR-2005-08. Computer Science Dept., Univ. of Chicago.
2005.
[ps]
-
Robust acoustic object detection.
Amit, Y., Koloydenko, A. and Niyogi, P.
Journal of the Acoustical Society of America, Vol. 118 (4), October, 2005.
(Also Tech. Report, No. 520. Department of Statistics, University of
Chicago, May, 2002. )
[pdf]
- Towards a Computational Model of Human Speech Perception.
P. Niyogi
Proceedings of the Conference on Sound to Sense,
MIT, 2004. (In Honor of Ken Stevens' 80th birthday)
[pdf]
- Detecting and Interpreting Acoustic Features
with Support Vector Machines.
C. Burges and P. Niyogi.
Tech. Report TR-2002-02. Computer Science Dept., Univ. of Chicago.
2002.
[ps]
- The Voicing Feature for Stop
Consonants: Recognition Experiments with Continuously Spoken
Alphabets.
P. Niyogi and P. Ramesh.
Speech Communication. Vol. 41, pp. 349-367, 2003.
[pdf]
- Detecting Stop Consonants in
Continuous Speech.
P. Niyogi and M. M. Sondhi.
Journal of the Acoustical Society of America. 111 (2), February, 2002.
[pdf]
- A Feature Based Representation
for Audio Visual Speech Recognition.
P. Niyogi, E. Petajan, J. Zhong.
Proceedings of the Audio Visual Speech Conference,
Santa Cruz, CA, 1999.
[pdf]
- Distinctive Feature Detection
using Support Vector Machines
P. Niyogi, C. Burges, P. Ramesh.
Proceedings of the International Conference on Acoustics, Speech,
and Signal Processing,
Phoenix, Arizona, 1999.
[pdf]
-
Discriminative Gaussian Mixture Models for Speaker Identification.
C. Burges, S. Chari, P. Niyogi, and C. Nohl.
preprint (short version presented at NIPS-Workshop
on Large Margin Classifiers, Dec., 1998).
[ps]
- Incorporating Voice Onset Time to
Improve Letter Recognition Accuracies.
P. Niyogi and P. Ramesh.
Proceedings of the IEEE International Conf. on
Acoustics, Speech and Signal Processing,
pp. 13-16. Seattle, WA, May 1998.
(superseded by journal (Speech Communication) version above.)
- The Voicing Feature for Stop
Consonants: Acoustic-Phonetic Analyses and ASR Experiments.
P. Ramesh and P. Niyogi.
Proceedings of the International Conference on Spoken Language
Processing, Sydney, Australia, Nov. 30-Dec. 4, 1998.
(superseded by journal (Speech Communication) version above.)
- A Detection Framework for
Locating Phonetic Events.
P. Niyogi, P. Mitra, M. M. Sondhi.
Proceedings of the International Conference on Spoken Language
Processing, Sydney, Australia, Nov. 30-Dec. 4, 1998.
- Modelling Speaker Variability and Imposing Speaker
Constraints in Phonetic Classification.
P. Niyogi.
LCS Tech-Report-533, MIT, Feb.,1992. (Version of S.M. Thesis).
- Correlation Analysis of Vowels and their
Application to Speech Recognition.
P. Niyogi and V. W. Zue.
Proceedings of EUROSPEECH, Genoa, Italy, 1991.
Miscellaneous
- A PC-Based Tabla Beat recognition
system.
P. Niyogi and G. K. Sinha.
Proceedings of the Indian Conference on Computers and
Communications, BARC, September, 1988.
- A PC-Based Tabla Beat Recognition System.
P. Niyogi.
Bachelor's Thesis submitted to Indian Institute of Technology, New
Delhi. (joint with G.K.Sinha)