Double-descent refers to the unexpected drop in test loss of a learning
...
This paper proposes the Hierarchical Functional Maximal Correlation Algo...
A bilateral (i.e., upper and lower) bound on the mean-square error under...
Due to privacy or commercial constraints, large pre-trained language mod...
We analyze the generalization ability of joint-training meta learning
al...
We consider learning a fair predictive model when sensitive attributes a...
It is known that neural networks have the problem of being over-confiden...
Various approaches have been developed to upper bound the generalization...
This paper provides an exact characterization of the expected generaliza...
We study the potential of data-driven deep learning methods for separati...
We study the problem of single-channel source separation (SCSS), and foc...
Generalization error bounds are essential to understanding machine learn...
Due to privacy, storage, and other constraints, there is a growing need ...
We provide an information-theoretic analysis of the generalization abili...
Selective regression allows abstention from prediction if the confidence...
Bounding the generalization error of a supervised learning algorithm is ...
As machine learning algorithms grow in popularity and diversify to many
...
A framework previously introduced in [3] for solving a sequence of stoch...
We show that model compression can improve the population risk of a
pre-...
A mutual information based upper bound on the generalization error of a
...
While recommendation systems generally observe user behavior passively, ...
Model change detection is studied, in which there are two sets of sample...
A framework is introduced for actively and adaptively solving a sequence...
The problem of universal outlying sequence detection is studied, where t...