Statistical Learning
Sample based Explanations via Generalized Representers
We propose a general class of sample based explanations of machine learning models, which we term generalized representers . To measure the effect of a training sample on a model's test prediction, generalized representers use two components: a global sample importance that quantifies the importance of the training point to the model and is invariant to test samples, and a local sample importance that measures similarity between the training sample and the test point with a kernel.
Appendix 1 A Investigation of Embedding Dynamics
We investigated if there are underlying structures within the embeddings during their evolution.
Dynamic Tensor Decomposition via Neural Diffusion-Reaction Processes
Tensor decomposition is an important tool for multiway data analysis.
Data-Informed Geometric Space Selection
Geometric representation learning (e.g., hyperbolic and spherical geometry) has proven to be efficacious in solving many intricate machine learning tasks.
