Uploaded August 2026 | Updated November 2026, 1 day ago
Fan Chen (MIT)
https://simons.berkeley.edu/talks/fan-chen-mit-2026-08-03
Diffusion Generative Modeling: Progress and Next Steps
We present an algorithmic framework for high-accuracy sampling using unbiased stochastic queries, with two main applications:
Algorithms for diffusion model sampling which obtain $\delta$-error in $\mathrm{polylog}(1/\delta)$ steps, given access to $\widetilde O(\delta)$-accurate score estimates in $L^2$. This is an exponential improvement over all previous results. (ICML 2026, arxiv.org/abs/2602.01338)
High-accuracy guarantees for log-concave sampling -- that is, iteration and query complexities which scale as $\mathrm{polylog}(1/\delta)$, where $\delta$ is the desired target accuracy -- are achievable using stochastic gradients with subexponential tails. Notably, this exhibits a separation with the problem of convex optimization, where stochasticity (even additive Gaussian noise) in the gradient oracle incurs $\mathrm{poly}(1/\delta)$ queries. (CoLT 2026, arxiv.org/abs/2602.14342)
Fan Chen (MIT)
https://simons.berkeley.edu/talks/fan-chen-mit-2026-08-03
Diffusion Generative Modeling: Progress and Next Steps
We present an algorithmic framework for high-accuracy sampling using unbiased stochastic queries, with two main applications:
Algorithms for diffusion model sampling which obtain $\delta$-error in $\mathrm{polylog}(1/\delta)$ steps, given access to $\widetilde O(\delta)$-accurate score estimates in $L^2$. This is an exponential improvement over all previous results. (ICML 2026, arxiv.org/abs/2602.01338)
High-accuracy guarantees for log-concave sampling -- that is, iteration and query complexities which scale as $\mathrm{polylog}(1/\delta)$, where $\delta$ is the desired target accuracy -- are achievable using stochastic gradients with subexponential tails. Notably, this exhibits a separation with the problem of convex optimization, where stochasticity (even additive Gaussian noise) in the gradient oracle incurs $\mathrm{poly}(1/\delta)$ queries. (CoLT 2026, arxiv.org/abs/2602.14342)










