Search papers, labs, and topics across Lattice.
Max Planck Institute for Intelligent Systems, T眉bingen
2
0
4
OT-ICA achieves superior performance in independent component recovery by maximizing the Wasserstein distance, challenging the dominance of traditional proxy-based methods.
KL divergence can fool you: matching a teacher's predictions doesn't guarantee preserving its internal representations, but distilling with logit distance does.
