通过稀疏性正则化，让扩散模型生成更快更省资源
Regularization can make diffusion models more efficient
- 用稀疏性正则化降低数据内在维度对计算量的影响
- 实验证明稀疏化可实现更低成本下的更优生成质量
- 适合关注高效扩散模型的算法研究者与工程落地人员
扩散模型是生成式AI的关键架构，但其主要缺点是计算开销大。本研究指出，稀疏性这一在统计学中广为人知的概念，可为构建更高效的扩散流水线提供路径。数学证明表明，稀疏性可将输入维度对计算复杂度的影响，降低至数据内在维度的水平。实验结果证实，引入稀疏性确实能在更低计算成本下生成更优样本。
原文摘要 · Abstract (English)
Diffusion models are one of the key architectures of generative AI. Their main drawback, however, is the computational costs. This study indicates that the concept of sparsity, well known especially in statistics, can provide a pathway to more efficient diffusion pipelines. Our mathematical guarantees prove that sparsity can reduce the input dimension's influence on the computational complexity to that of a much smaller intrinsic dimension of the data. Our empirical findings confirm that inducing sparsity can indeed lead to better samples at a lower cost.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。