Search papers, labs, and topics across Lattice.
3
0
6
3
A single controller can now robustly learn stochastic transport across a range of initial distribution shifts, outperforming standard SB and noise augmentation on challenging tasks.
Entropic transport descent transforms particle-based variational inference by leveraging optimal transport principles, achieving superior performance in high-dimensional and multimodal distributions.
Information-theoretic limits on control performance are now computable even when feedback matters most, thanks to a new bound that self-consistently accounts for the controller's impact on sensor information.
