退火放松的投机解码用于更快的自回归图像生成
Annealed Relaxation of Speculative Decoding for Faster Autoregressive Image Generation
AI总结：
本文提出COOL-SD，通过退火放松的投机解码方法提升自回归图像生成的速度与质量。
摘要：
尽管在自回归图像生成方面取得了显著进展，但推断仍然缓慢，这是由于AR模型的序列性质和图像标记的模糊性，即使使用投机解码也是如此。最近的研究试图通过放松的投机解码来解决这个问题，但缺乏理论基础。在本文中，我们建立了放松SD的理论基础，并提出了COOL-SD，这是一种基于两个关键洞察的退火放松的投机解码。第一个分析了目标模型与放松投机解码之间的总变分（TV）距离，并得到了一个最优重采样分布，该分布最小化了距离的上界。第二个利用扰动分析揭示了放松投机解码中的退火行为，促使我们的退火设计。共同，这些洞察使COOL-SD能够以可比的质量生成图像，或者在相似延迟下实现更好的质量。实验验证了COOL-SD的有效性，显示其在速度-质量权衡方面优于先前方法。
英文摘要：
Despite significant progress in autoregressive image generation, inference remains slow due to the sequential nature of AR models and the ambiguity of image tokens, even when using speculative decoding. Recent works attempt to address this with relaxed speculative decoding but lack theoretical grounding. In this paper, we establish the theoretical basis of relaxed SD and propose COOL-SD, an annealed relaxation of speculative decoding built on two key insights. The first analyzes the total variation (TV) distance between the target model and relaxed speculative decoding and yields an optimal resampling distribution that minimizes an upper bound of the distance. The second uses perturbation analysis to reveal an annealing behaviour in relaxed speculative decoding, motivating our annealed design. Together, these insights enable COOL-SD to generate images faster with comparable quality, or achieve better quality at similar latency. Experiments validate the effectiveness of COOL-SD, showing consistent improvements over prior methods in speed-quality trade-offs.
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。
