Statistical Learning
Self-SupervisedLearningvia MaximumEntropyCoding
Self-supervised learning (SSL) aims to learn rich and meaningful representations without relying onhumanannotations.
Residual Flows for Invertible Generative Modeling
Tian Qi Chen, Jens Behrmann, David K. Duvenaud, Joern-Henrik Jacobsen
Neural Information Processing Systems http://nips.cc/
Heterogeneous Multi-output Gaussian Process Prediction
Pablo Moreno-Muñoz, Antonio Artés, Mauricio Álvarez
Neural Information Processing Systems http://nips.cc/
On the Target-kernel Alignment: a Unified Analysis with Kernel Complexity
Y et, under the strongly-aligned regime, KM suffers the saturation effect, while TKM can be continuously improved as the alignment becomes stronger. This further implies that TKM has a strong ability to capture the strong alignment and provide a theoretically guaranteed solution to eliminate the phenomena of saturation effect.
Modelling sparsity, heterogeneity, reciprocity and community structure in temporal interaction data
Xenia Miscouridou, Francois Caron, Yee Whye Teh
Neural Information Processing Systems http://nips.cc/
Minimal Variance Sampling in Stochastic Gradient Boosting
Differentsamplingapproaches were proposed, where probabilities are not uniform, and it is not currently clear which approach is the most effective. In this paper, we formulate the problem of randomization in SGB in terms of optimization of sampling probabilities to maximize the estimation accuracy of split scoring used to train decision trees.
