DiffNAS：通过提示引导扩散模型以获取更优架构
DiffNAS: Bootstrapping Diffusion Models by Prompting for Better Architectures
AI总结：
本文提出DiffNAS，利用GPT-4作为超网络并借助搜索记忆和RFID代理，通过快速收敛训练策略，将扩散模型架构搜索效率提升2倍，并在CIFAR10上使FID改善0.37。
摘要：
扩散模型最近在合成数据上展现出了卓越的性能。在选定一条扩散路径后，基础模型（如UNet）作为去噪自编码器运行，主要预测需要逐步消除的噪声。因此，采用与预期预算相匹配的模型对于促进优越的合成性能至关重要。在本文中，我们细致地分析了扩散模型，并设计了一种基础模型搜索方法，称为“DiffNAS”。具体来说，我们利用GPT-4作为超网络来加速搜索，并辅以搜索记忆以增强结果。此外，我们采用RFID作为代理，以快速对GPT-4产生的实验结果进行排序。我们还采用了快速收敛的训练策略以提高搜索效率。严格的实验证实，我们的算法在基于GPT的场景下可以将搜索效率提高2倍，同时在CIFAR10上相对于基准IDDPM算法，FID达到了2.82，改善了0.37。
英文摘要：
Diffusion models have recently exhibited remarkable performance on synthetic data. After a diffusion path is selected, a base model, such as UNet, operates as a denoising autoencoder, primarily predicting noises that need to be eliminated step by step. Consequently, it is crucial to employ a model that aligns with the expected budgets to facilitate superior synthetic performance. In this paper, we meticulously analyze the diffusion model and engineer a base model search approach, denoted "DiffNAS". Specifically, we leverage GPT-4 as a supernet to expedite the search, supplemented with a search memory to enhance the results. Moreover, we employ RFID as a proxy to promptly rank the experimental outcomes produced by GPT-4. We also adopt a rapid-convergence training strategy to boost search efficiency. Rigorous experimentation corroborates that our algorithm can augment the search efficiency by 2 times under GPT-based scenarios, while also attaining a performance of 2.82 with 0.37 improvement in FID on CIFAR10 relative to the benchmark IDDPM algorithm.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
