Statistical Learning
Federated Multi-Task Learning under a Mixture of Distributions
The algorithms' convergence is analyzed through a novel federated surrogate optimization framework, which can be of general interest.
Neural FFTs for Universal Texture Image Synthesis
Synthesizing larger texture images from a smaller exemplar is an important task in graphics and vision.
Learning Enhanced Representations for Tabular Data via Neighborhood Propagation
Recently, as shown by Papernot and McDaniel (2018), feeding in neighbors of the target as input can improve the robustness of data representations and help the model generalize better to out-of-distribution samples.
A Theoretical Analysis of Fine-tuning with Linear Teachers
Fine-tuning is a common practice in deep learning, achieving excellent generalization results on downstream tasks using relatively little training data.
A Appendix
See the "Ranker" block of Figure 1.
Label Disentanglement in Partition-based Extreme Multilabel Classification
For instance, the label "Apple" can be the fruit or the brand name, which