Showing stat.MLShow all
3 papers · 1 filter
stat.ML2026
Non-Asymptotic Error Bounds for SMC with Biased Proposals: Application to Conditional Diffusion Sampling
Stanislas Strasman, Gabriel Victorino Cardoso, Sylvain Le Corff +2
Sequential Monte Carlo (SMC) methods are a natural tool for post-hoc conditioning of pretrained generative models, but in many applications the mutation kernels used by the particl…
stat.ML2026
Non-asymptotic Convergence of Stochastic Gradient Descent in Score-based Generative Models
Stanislas Strasman, Sobihan Surendran, Sylvain Le Corff
Score-based Generative Models (SGMs) have achieved impressive performance in data generation across a wide range of applications. While the statistical properties of their sampling…
stat.ML2026
Increasing Missingness to Reduce Bias: Richardson-SGD with Missing Data
Ferdinand Genans, Erwan Scornet
Stochastic gradient methods are central to modern large-scale learning, but their use with incomplete covariates remains delicate since imputation schemes generally introduce syste…