Search papers, labs, and topics across Lattice.
Collège de France, Paris, France, Flatiron Institute, New York, USA
2
0
3
Skip the GANs: this kernel method generates complex data like financial time series and images without any training, just by solving linear systems.
Escape the MCMC slowdown: this diffusion-based approach efficiently samples maximum entropy distributions by directly guiding moments, offering a practical alternative for high-dimensional uncertainty quantification.
