Asia
Decentralized, Communication-and Coordination-free Learning in Structured Matching Markets
We study the problem of online learning in competitive settings in the context of two-sided matching markets.
73fed7fd472e502d8908794430511f4d-Supplemental.pdf
Our results motivate a natural partial order over covariate shifts that provides a sufficient condition for determining when the shift will harm (or even help) test performance.
Overparameterization Improves Robustnessto Covariate Shiftin High Dimensions
Inthisconte the (asymptotic) derived [68].
ContrastiveActiveInference
Active inference is a unifying theory for perception and action resting upon the idea that the brain maintains an internal model of the world by minimizing free energy.
A Simple Yet Effective Strategy to Robustify the Meta Learning Paradigm
Meta learning is a promising paradigm to enable skill transfer across tasks.
A Simple Yet Effective Strategy to Robustify the Meta Learning Paradigm Qi Wang
Meta learning is a promising paradigm to enable skill transfer across tasks.
