Jun Zhu, Chongxuan Li, Jianfei Chen, Fan Bao, Cheng Lu, Kaiwen Zheng
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Score-based generative models have excellent performance in terms of generation quality and likelihood. They model the data distribution by matching a parameterized score network with first-order data score functions. The score network can be used to define an ODE ("score-based diffusion ODE") for exact likelihood evaluation. However, the relationship between the likelihood of the ODE and the score matching objective is unclear. In this work, we prove that matching the firstorder score is not sufficient to maximize the likelihood of the ODE, by showing a gap between the maximum likelihood and score matching objectives. To fill up this gap, we show that the negative likelihood of the ODE can be bounded by controlling the first, second, and third-order score matching errors; and we further present a novel highorder denoising score matching method to enable maximum likelihood training of score-based diffusion ODEs. Our algorithm guarantees that the higher-order matching error is bounded by the training error and the lower-order errors. We empirically observe that by high-order score matching, score-based diffusion ODEs achieve better likelihood on both synthetic data and CIFAR-10, while retaining the high generation quality.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2206.08265")
get_code_for_paper("2206.08265")
have("2206.08265")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2206.08265.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2206.08265)
Connect an agent — have() is free.