Statistical Learning
Extracting Relationships by Multi-Domain Matching
Yitong Li, michael Murias, geraldine Dawson, David E. Carlson
Neural Information Processing Systems http://nips.cc/
Inferring Networks From Random Walk-Based Node Similarities
Jeremy Hoskins, Cameron Musco, Christopher Musco, Babis Tsourakakis
For the effective resistance metric, we show that with just a small subset of measurements, one can learn a large fraction of edges in a social network. We also show that it is possible to learn a graph which accurately matches the underlying network on all other effective resistances.
The Price of Privacy for Low-rank Factorization
Neural Information Processing Systems http://nips.cc/
Algorithms and Theory for Multiple-Source Adaptation
Judy Hoffman, Mehryar Mohri, Ningshan Zhang
Moreover, we give new algorithms for determining the distribution-weighted combination solution for the cross-entropy loss and other losses.
Leveraged volume sampling for linear regression
Michal Derezinski, Manfred K. K. Warmuth, Daniel J. Hsu
Surprisingly we show that volume sampling can have poor behavior when we require a very accurate approximation - indeed worse than some i.i.d.
Disconnected Manifold Learning for Generative Adversarial Networks
Mahyar Khayatkhoei, Maneesh K. Singh, Ahmed Elgammal
Next, we show how using a collection of generators can address this problem, providing new insights into the success of such multi-generator GANs.
Learning Deep Disentangled Embeddings With the F-Statistic Loss
Karl Ridgeway, Michael C. Mozer
Disentangling methods aim to make explicit compositional or factorial structure.
Multitask Boosting for Survival Analysis with Competing Risks
Alexis Bellot, Mihaela van der Schaar
Neural Information Processing Systems http://nips.cc/
Compact Representation of Uncertainty in Clustering
Craig Greenberg, Nicholas Monath, Ari Kobren, Patrick Flaherty, Andrew McGregor, Andrew McCallum
Neural Information Processing Systems http://nips.cc/
Bayesian Alignments of Warped Multi-Output Gaussian Processes
Markus Kaiser, Clemens Otte, Thomas Runkler, Carl Henrik Ek
The proposed model allows for both arbitrary alignments of the inputs and non-parametric output warpings to transform the observations. This gives rise to multiple deep Gaussian process models connected via latent generating processes.