Statistical Learning
A causal view of compositional zero-shot recognition
Unfortunately, learning systems struggle with compositional generalization because they often build on features that are correlated with class labels even if they are not "essential" for the class.
A Bayesian Nonparametrics View into Deep RepresentationsSupplementary material A Collapsed Gibbs Sampling for DP-GMM
Here we describe CGS in more details. Eqn. 10 we obtain: null null Expression under the last integral in Eqn. 13 is tractable, thanks to the conjugacy of the Normal-inverse-Wishart prior to the Gaussian likelihood. Finally, posterior predictive density (10) can be written as a mixture of multivariate Student's CIFAR experiments used the standard train/test split. Results for architectures not included in Section 4 are summarized in Fig. C.1. Table C.1: CNN architectures used in experiments (Section 4).
A Framework for Individualizing Predictions of Disease Trajectories by Exploiting Multi-Resolution Structure
Neural Information Processing Systems http://nips.cc/
Comparing distributions: $\ell_1$ geometry improves kernel two-sample testing
Are two sets of observations drawn from the same distribution? This problem is a two-sample test. Kernel methods lead to many appealing properties.
Practical and Optimal LSH for Angular Distance
The method relies on the notion of locality-sensitive hash functions .
Inferring Algorithmic Patterns with Stack-Augmented Recurrent Nets
Neural Information Processing Systems http://nips.cc/
Interactive Control of Diverse Complex Characters with Neural Networks
Igor Mordatch, Kendall Lowrey, Galen Andrew, Zoran Popovic, Emanuel V. Todorov
Neural Information Processing Systems http://nips.cc/
Retrosynthesis Prediction with Conditional Graph Logic Network
Hanjun Dai, Chengtao Li, Connor Coley, Bo Dai, Le Song
Retrosynthesis is one of the fundamental problems in organic chemistry.