1 citations · 1 across the 1 of their papers we have counts for
2 papers
cs.LG2023★ 1 cited
On diffusion-based generative models and their error bounds: The log-concave case with full convergence estimates
Stefano Bruno, Ying Zhang, Dong-Young Lim +2
We provide full theoretical guarantees for the convergence behaviour of diffusion-based generative models under the assumption of strongly log-concave data distributions while our…
cs.LG2021
Polygonal Unadjusted Langevin Algorithms: Creating stable and efficient adaptive algorithms for neural networks
Dong-Young Lim, Sotirios Sabanis
We present a new class of Langevin based algorithms, which overcomes many of the known shortcomings of popular adaptive optimizers that are currently used for the fine tuning of de…