Search papers, labs, and topics across Lattice.
School of Mathematical Sciences, Fudan University, Shanghai 200433, China
2
0
4
Mirror Descent, a workhorse of large-scale optimization, now has a Riemannian generalization with convergence guarantees, opening doors to efficient optimization on curved spaces.
LLMs may grasp the broad strokes of causal strategies, but struggle with the devilish details of research design, as revealed by a new benchmark separating causal identification from estimation.
