Public articles linked to the same research event.
arXiv The work proposes affine post-processing: splitting a fixed score-estimation compute budget across multiple signal levels, querying the base estimator at each, and pooling the estimates by a linear combination (ridge regression / linear smoother); it proves that at matched compute this split-and-pool estimate has lower score error than a single on-policy estimate, and reports up to two orders of magnitude smaller terminal Wasserstein distance on ill-conditioned Gaussians, multimodal mixtures, and high-dimensional targets.
The work proposes affine post-processing: splitting a fixed score-estimation compute budget across multiple signal levels, querying the base estimator at each, and pooling the estimates by a linear combination (ridge regression / linear smoother); it proves that at matched compute this split-and-pool estimate has lower score error than a single on-policy estimate, and reports up to two orders of magnitude smaller terminal Wasserstein distance on ill-conditioned Gaussians, multimodal mixtures, and high-dimensional targets.
The work proposes affine post-processing: splitting a fixed score-estimation compute budget across multiple signal levels, querying the base estimator at each, and pooling the estimates by a linear combination (ridge regression / linear smoother); it proves that at matched compute this split-and-pool estimate has lower score error than a single on-policy estimate, and reports up to two orders of magnitude smaller terminal Wasserstein distance on ill-conditioned Gaussians, multimodal mixtures, and high-dimensional targets.
The work proposes affine post-processing: splitting a fixed score-estimation compute budget across multiple signal levels, querying the base estimator at each, and pooling the estimates by a linear combination (ridge regression / linear smoother); it proves that at matched compute this split-and-pool estimate has lower score error than a single on-policy estimate, and reports up to two orders of magnitude smaller terminal Wasserstein distance on ill-conditioned Gaussians, multimodal mixtures, and high-dimensional targets.