Search papers, labs, and topics across Lattice.
2
0
4
GMD algorithms, previously seen as a novel generative framework, can be understood as directly targeting fixed points of Wasserstein Gradient Flows, offering a new perspective on their optimization process.
Unlock asymptotically normal and semiparametrically efficient estimators in adaptive data collection by using a novel target-specific condition called "directional stability," which is weaker than previous target-agnostic conditions.
