4 papers · 1 filter
Is Spurious Correlation Removal Always Learnable?
Yibo Zhou, Bo Li, Hai-Miao Hu +3
Invariant learning can fail even when the invariant structure is statistically identifiable. We show a conditional computational barrier: under a black-box samplable supervised spa…
Invariant-Feature Subspace Recovery: A New Class of Provable Domain Generalization Algorithms
Haoxiang Wang, Gargi Balasubramaniam, Haozhe Si +2
Domain generalization asks for models trained over a set of training environments to generalize well in unseen test environments. Recently, a series of algorithms such as Invariant…
Gradual Domain Adaptation: Theory and Algorithms
Yifei He, Haoxiang Wang, Bo Li +1
Unsupervised domain adaptation (UDA) adapts a model from a labeled source domain to an unlabeled target domain in a one-off way. Though widely applied, UDA faces a great challenge…
Global Convergence and Generalization Bound of Gradient-Based Meta-Learning with Deep Neural Nets
Haoxiang Wang, Ruoyu Sun, Bo Li
Gradient-based meta-learning (GBML) with deep neural nets (DNNs) has become a popular approach for few-shot learning. However, due to the non-convexity of DNNs and the bi-level opt…