Out-of-distribution (OOD) generalization is a critical ability for deep
...
Layer normalization (LN) is a widely adopted deep learning technique
esp...
Deep models are dominating the artificial intelligence (AI) industry sin...
We show that the canonical approach for training differentially private ...
Recent work reported the label alignment property in a supervised learni...
Modern machine learning systems achieve great success when trained on la...
Federated Learning (FL) is a prominent framework that enables training a...
Making predictions robust is an important challenge. A separate challeng...
In typical scenarios where the Federated Learning (FL) framework applies...
The dominant line of work in domain adaptation has focused on learning
i...
Ensuring fairness of machine learning (ML) algorithms is becoming an
inc...
Unsupervised domain adaptation is used in many machine learning applicat...
Out-of-distribution generalization is one of the key challenges when
tra...
Differential games, in particular two-player sequential games (a.k.a. mi...
Federated learning has emerged as a promising, massively distributed way...
Convergence to a saddle point for convex-concave functions has been stud...
Min-max formulations have attracted great attention in the ML community ...
Min-max optimization has attracted much attention in the machine learnin...
The expectation-maximization (EM) algorithm has been widely used in
mini...