Saved in:
Bibliographic Details
Main Authors: Bettencourt, Jesse, Wu, Xindi, Atzmon, Matan, Lucas, James, Lorraine, Jonathan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.21489
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918517334343680
author Bettencourt, Jesse
Wu, Xindi
Atzmon, Matan
Lucas, James
Lorraine, Jonathan
author_facet Bettencourt, Jesse
Wu, Xindi
Atzmon, Matan
Lucas, James
Lorraine, Jonathan
contents Pretrained diffusion models serve as frozen teachers feeding downstream pipelines such as text-to-3D, single-step distillation, and data attribution. The teacher gradients these pipelines consume are Monte Carlo (MC) expectations over noise levels and Gaussian noise samples; their estimator variance dominates compute cost because each draw requires expensive upstream work (rendering, simulation, encoding). We introduce CARV, a compute-aware variance-accounting framework that motivates a hierarchical MC estimator: amortize the expensive upstream computation over cheap diffusion-noise resamples, sharpened by timestep importance sampling and a stratified-inverse-CDF construction. In our text-to-3D distillation and attribution experiments, CARV delivers 2-3x effective compute multipliers (most from amortized reuse; ~25% additional from IS+stratification) without changing the objective; in single-step distillation, the same techniques cut gradient variance by an order of magnitude but do not improve downstream FID, marking the regime where MC variance is no longer the bottleneck.
format Preprint
id arxiv_https___arxiv_org_abs_2605_21489
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Variance Reduction for Expectations with Diffusion Teachers
Bettencourt, Jesse
Wu, Xindi
Atzmon, Matan
Lucas, James
Lorraine, Jonathan
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Computation
65C05
I.2.6; G.3
Pretrained diffusion models serve as frozen teachers feeding downstream pipelines such as text-to-3D, single-step distillation, and data attribution. The teacher gradients these pipelines consume are Monte Carlo (MC) expectations over noise levels and Gaussian noise samples; their estimator variance dominates compute cost because each draw requires expensive upstream work (rendering, simulation, encoding). We introduce CARV, a compute-aware variance-accounting framework that motivates a hierarchical MC estimator: amortize the expensive upstream computation over cheap diffusion-noise resamples, sharpened by timestep importance sampling and a stratified-inverse-CDF construction. In our text-to-3D distillation and attribution experiments, CARV delivers 2-3x effective compute multipliers (most from amortized reuse; ~25% additional from IS+stratification) without changing the objective; in single-step distillation, the same techniques cut gradient variance by an order of magnitude but do not improve downstream FID, marking the regime where MC variance is no longer the bottleneck.
title Variance Reduction for Expectations with Diffusion Teachers
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Computation
65C05
I.2.6; G.3
url https://arxiv.org/abs/2605.21489