Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
the Chinese University of Hong Kong (Shenzhen)
2
0
2
Stochastic nonconvex-strongly-concave minimax optimization is officially closed: new $\Omega(\kappa \epsilon^{-4})$ and $\Omega(\kappa^{3/2}\epsilon^{-3})$ lower bounds prove that standard first-order algorithms have already hit the fundamental limits of sample complexity.
A single-loop algorithm for bilevel optimization reduces oracle complexity by orders of magnitude compared to traditional double-loop methods.