Previous Invited Speakers
2012 Pictures
2011 Pictures
2010 Pictures
2009 Pictures
2008 Pictures
2007 Pictures
2006 Pictures
2005 Pictures
2004 Pictures
2003 Pictures
2002 Pictures
2001 Pictures
2000 Pictures
2012 Program
2011 Program
2010 Program
2009 Program
2008 Program
2007 Program
2006 Program
2005 Program
2004 Program
2003 Program
2002 Program
2001 Program
2000 Program
1999 Program
NIPS Online

Learning@Snowbird 2006: Program


Andrew Fitzgibbon (Microsoft Research, Cambridge) Matrix factorization with missing data
Brendan Frey (University of Toronto)Explorations into the cellular transcriptome
Don Geman (Johns Hopkins University)Small-Sample Learning in Computational Biology
Carlos Guestrin (Carnegie Mellon University)Sensor Networks, Gaussian Processes and Constrained Experimental Design
Ralf Herbrich (Microsoft Research, Cambridge)Bayesian ranking
Larry Jackel (DARPA IPTO/TTO)What Are the DARPA Ground Robots Learning?
David Stork (Ricoh)Did the great masters "cheat" using optics? Computer image analysis of Renaissance masterpieces sheds light on a controversial theory

ORAL PRESENTATIONS (20 minute talks + optional poster)

010P. Baldi (UCI) and L. Wu (UCI)
A Scalable Machine Learning Approach to the Game of Go
027S. V. N. Vishwanathan, Nicol N. Schraudolph (National ICT Australia); Mark W. Schmidt, Kevin Murphy (U. British Columbia)
Accelerated Training of Conditional Random Fields with Stochastic Meta-Descent
032P. Wiesing (TU Berlin), O. Beck (TU Berlin), L. Schwabe (TU Berlin), J. Marino (U. A Coruna), J. Schummers (MIT), D. Lyon (Salk Institute), M. Sur (MIT), and Obermayer K. (TU Berlin)
The Operating Regime of Cortical Computation
035Neil Lawrence (U. Sheffield), Joaquin Quiñonero-Candela (Fraunhofer FIRST.IDA)
Local Distance Preservation in the GP-LVM through Back Constraints
041D. Huttenlocher (Cornell U.) and D. Crandall (Cornell U.)
Learning and Recognizing Objects Without Relying on Feature Detection
042H. Daume III (USC/ISI), John Langford (TTI-C) and Daniel Marcu (USC/ISI)
Search-based Structured Prediction
043D. Cohn (Google, Inc.), and D. Verma (University of Washington)
Recursive Attribute Factoring
046N. Le Roux (U. de Montreal) and Y. Bengio (U. de Montreal)
Continuous Neural Networks
054J.A. Bagnell (CMU), N.D. Ratliff (CMU), M. A. Zinkevich (Alberta)
Sub-gradient Method Structured Learning and Mobile Robotics
056Frank DiMaio (UW-Madison), Jude Shavlik (UW-Madison), and George Phillips (UW-Madison)
Tracing Protein Backbones in Electron Density Maps using a Markov Random Field Model
057Sang Min Oh (GeorgiaTech) and James M. Rehg (GeorgiaTech) and Frank Dellaert (Georgia Tech)
On-line Learning of the Traversability of Unstructured Terrain for Outdoor Robot Navigation
059R. Hadsell, P. Sermanet, J. Ben, J. Han, S. Chopra, M. Ranzato, Y. Sulsky, B. Flepp, U. Muller, Yann LeCun (NYU and Net-Scale Technologies)
On-Line Learning of Long-Range Obstacle Detection for Off-Road Robots
066C. Sminchisescu (TTI-C), Atul Kanaujia (Rutgers University), Dimitris Metaxas (Rutgers University)
Bidirectional Model Learning for Visual Inference
067P. Haffner (AT&T Labs-Research)
AdaBoost is Maximum Entropy over the Error Distribution
068Luis Perez-Breva (MIT), Luis E. Ortiz (MIT), Chen-Hsiang Yeang (UC Santa Cruz) and Tommi Jaakkola (MIT)
A Game-Theoretic Approach to Protein-DNA Binding
070Fei Sha (U. of Pennsylvania), and Lawrence K. Saul (U. of Pennsylvania)
Large margin Gaussian mixture modeling
083N. de Freitas (UBC)
Recent Advances in Particle Methods
088M. Ranzato (NYU), and Y. LeCun (NYU)
Energy-based model for unsupervised learning of sparse overcomplete representations
094L. Torresani (Riya, Inc.), P. Hackney (Integrated Movement Studies), and C. Bregler (New York University)
Learning to Synthesize Motion Styles
098J. Blitzer, K. Crammer, R. McDonald, F. Pereira (University of Pennsylvania)
Structural Correspondences for Transfer Learning
099Françoise Soulié Fogelman, KXEN
Data mining in the real world : what do we need & what do we have
100D. Dueck (U. Toronto) and B.J. Frey (U. Toronto)
Is it better to cluster using belief propagation or linear programming?
102N. Srebro (U. Toronto), and G. Shakhnarovich (Brown), and S. Roweis (U. Toronto)
When is clustering hard?

SPOTLIGHT PRESENTATIONS (10 minute talks + poster)

024R. Der and D. D. Lee (U. Pennsylvania)
To boldly go where no kernel has gone before: Machine learning in l_p semi-inner product spaces
055C. Murray and G. Gordon (CMU CALD)
Multi-Robot Negotiation: Approximating the Set of Subgame Perfect Equilibria in General-Sum Stochastic Games
064S. Ben-David (U. Waterloo), and U. von Luxburg (Fraunhofer IPSI), and D. Pal (U. Waterloo)
A sober look at clustering stability
086R. Hadsell (Courant Institute, NYU), S. Chopra (Courant Institute, NYU), and Y. LeCun (Courant Institute, NYU)
Dimensionality Reduction by Learning an Invariant Mapping
097PE Barbano (YALE), M. Spivak (NYU), L. Greengard (NYU)
A new exploratory Tool for Biological Network Dynamics


001Ciprian Chelba (Microsoft Research)
Acoustic Sensitive Language Model Perplexity for Automatic Speech Recognition
007Bruce Denby (Université Pierre et Marie Curie)
Talking without Speaking : An Overview of the OUISPER Project
008S. Kiritchenko, S. Matwin, R. Nock, F. Famili
Learning in the Presence of Class Hierarchies
014C. Pedersen (U. Queensland), and J. Diederich (U. Queensland, American Univ. of Sharjah)
Human and machine learning based accent recognition
017M. Gupta (U. Washington)
Some recent research in nonparametric near-neighbor learning
018Brendt Wohlberg and Kevin Vixie (Los Alamos National Laboratory)
Template Matching With Invariance Based on Local Linear Transform Approximations
019Peng Zhao, Guilherme Rocha & Bin Yu (UC Berkeley)
Grouped and Hierarchical Model Selection through Composite Absolute Penalties (CAP)
020C.Alippi (Politecnico di Milano), and M.Roveri (Politecnico di Milano)
021L. Coin (Imperial College), Shu-Yi Su (Imperial College), David Balding (Imperial College)
Using Sparse Bayesian Learning
023E. Chang (UC Santa Barbara/Google), and M. Lyu (Chinese University Hong Kong)
A Unified Learning Paradigm for Web-scale Information Management
025Frank Dellaert (Georgia Institute of Technology)
Variable Elimination and the Bayes Tree Algorithm
026A. B. Owen (Stanford U)
A robust hybrid of lasso and ridge regression
028Christopher R. Wren (MERL) and Yuri A. Ivanov (MERL)
Boosted Haar Wavelets for Sensor Networks
029J. Diederich (U. Queensland, American Univ. of Sharjah)
Rule-Extraction from Support Vector Machines
030M. Braun (Fraunhofer Institute FIRST), and J. Buhmann (Swiss Federal Institute of Technology Zurich)
On Learning in Infinite Dimensional Kernel Feature Spaces
031Aurelie GOULON (ESPCI, Paris), Arthur DUPRAT (ESPCI, Paris), Gerard DREYFUS (ESPCI, Paris)
033Kai Puolamäki, Jarkko Salojärvi, Eerika Savia, and Samuel Kaski (Helsinki U. of Technology)
Discriminative MCMC
034Ashok Veeraraghavan ( University of Maryland, College Park) and Rama Chellappa (University of Maryland, College Park)
Learning the function space of an activity
037N. P. Cuntoor (U. Maryland), and R. Chellappa (U. Maryland)
Mixed State Models for Human Activities
039Ulrike von Luxburg (Fraunhofer IPSI), Shai Ben-David (University of Waterloo)
Prior Beliefs in Semi-Supervised Learning
040Baback Moghaddam (MERL), Yair Weiss (Hebrew University), Shai Avidan (MERL)
Spectral Bounds for Feature Selection & Sparse LDA
044T. Joachims (Cornell)
Training Linear SVMs in Linear Time
048M. Siracusa (MIT), and J. Fisher (MIT)
Modeling and Estimating Dynamic Dependency Structure : Applications to Audio-Visual Speaker Labeling
049Y. Bengio, D. Popovici, P. Lamblin, R. Garg, B. Cromp, and P.-J. L'Heureux (U. Montreal)
Discriminant Mixture of 3D Molecular Surface Models
050H. Narayanan (Univ. of Chicago), M. Belkin (Ohio State Univ.), P. Niyogi (Univ. of Cicago)
Volumes of Boundaries, Heat Propagation and Spectral Clustering
051D. Minnen, T. Starner, I. Essa, and C. Isbell (Georgia Tech)
Activity Discovery: Sparse Motifs from Multivariate Time Series
052A. Guta (U. Penn), D. Foster (U. Penn), L. Ungar (U. Penn)
Unsupervised learning of distance metrics
053Minyoung Kim (Rutgers) and Vladimir Pavlovic (Rutgers)
Efficient Discriminative Learning of Mixture of Bayesian Networks for Sequence Classification
058M. Holmes (Georgia Tech), and C. Isbell (Georgia Tech)
Looping Suffix Trees for Inference of Partially Observable Hidden State
060O. Berkman (Tel-Aviv University), and N. Intrator (Tel-Aviv University)
Robust Inference in Bayesian Networks
061N. Srebro (U. Toronto), and S. Ben-David (U. Waterloo)
Learning bounds for support vector machines with learned kernels
063Alexandru Niculescu-Mizil (Cornell University), and Rich Caruana (Cornell University)
Inductive Transfer for Bayesian Network Structure Learning
065T. Jebara (Columbia U.), B. Shaw (Columbia U.), and V. Shchogolev (Columbia U.)
B-Matching for Embedding
071A. Globerson (MIT), S. Roweis (U. Toronto)
Visualizing pairwise similarity via semidefinite programming
072M. Kim (Rutgers), Y. Jing (Georgia Tech.), V. Pavlovic (Rutgers), and J. M. Rehg (Georgia Tech.)
Discriminative Learning of Generative Models for Sequence Labeling Problems
073Maria-Florina Balcan (CMU), Alina Beygelzimer (IBM Watson), John Langford (TTI-Chicago)
Robust Reductions from Ranking to Classification
074R. Caruana (Cornell), C. Bucila (Cornell), A. Niculescu-Mizil (Cornell)
Model Compression
075G. Grudic and J. Mulligan
The Polynomial Mahalanobis Distance
077K. Chellapilla and J. Platt (Microsoft Research)
Redundant Bit Vectors for Handwriting Retrieval
078D. Verma (U. Washington, Seattle) and R.P.N. Rao (U. Washington, Seattle)
Graphical Models for Planning and Acting in Uncertain Environments
080O. Madani (Yahoo! Research)
Recall Systems
081Anthony Hoogs (GE Global Research) and Roderic Collins (GE Global Research)
Boundary Detection using Semantic, Hierarchical Category Models
084Gang Wu, Zhihua Zhang, Edward Y. Chang
Speeding up Support Vector Machines
085G. Shakhnarovich (Brown University), and J. W. Fisher (MIT)
Performance of approximate nearest-neighbor classification
090K. Q. Weinberger (UPenn), K. Crammer (UPenn), L. K. Saul (UPenn)
Local Distance Metric Learning for Large Margin
092Ian Fasel and Javier R. Movellan
Unsupervised Learning of Object Categories and Image Segmentations
093V. Punyakanok (U. of Illinois), and D. Roth (U. of Illinois)
Utility of Constraints in Structured Output Problems
096K. Kavukcuoglu (NYU), Y.LeCun (NYU), K. White (Yale), PE Barbano (Yale)
End-to-End Learning for Automatic Cell Phenotyping
103Matt L. Miller (NEC Labs America)
Linear Feature Discovery from Decision Boundary Normals
105Alex Vasilescu (MIT)
Manifold Decomposition and Low Dimensional Parameterization