Interesting papers coming up at NIPS'11

There's a number of accepted papers whose camera-ready versions have been posted already. Here are the ones I found interesting. I'll give further update on these after the conference.

• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials, P. Krähenbühl, V. Koltun
• Fast and Accurate k-means For Large Datasets, M. Shindler, A. Wong, A. Meyerson
• Hashing Algorithms for Large-Scale Learning, P. Li, A. Shrivastava, J. Moore, A. König
• Hogwild: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent, B. Recht, C. Re, S. Wright, F. Niu
• Generalizing from Several Related Classification Tasks to a New Unlabeled Sample, G. Blanchard, G. Lee, C. Scott
• How biased are maximum entropy models? J. Macke, I. Murray, P. Latham
• On Tracking The Partition Function, G. Desjardins, A. Courville, Y. Bengio
• Selecting Receptive Fields in Deep Networks, A. Coates, A. Ng
• Shallow vs. Deep Sum-Product Networks, O. Delalleau, Y. Bengio
• Statistical Tests for Optimization Efficiency, L. Boyles, A. Korattikara, D. Ramanan, M. Welling

Additionally, here's a non-NIPS preprint I came across that summarizes belief propagation and related algorithms. In particular, it turns out that state of the art algorithm for sphere packing, Divide and Concur is closely related to belief propagation.

• Message-passing Algorithms for Inference and Optimization, Jonathan S. Yedidia