比最多样化的模型更多样化：基于Mixture-UCB老虎机算法的生成模型最优混合
Be More Diverse than the Most Diverse: Optimal Mixtures of Generative Models via Mixture-UCB Bandit Algorithms
AI总结：
针对生成模型选择仅考虑单模型的局限，本研究将最优混合模型选择建模为多臂老虎机问题，提出Mixture-UCB算法，可高效找到优于单个模型的生成模型最优混合体，并验证了其在文本、图像生成任务中的有效性。
摘要：
生成模型存在多种训练算法和架构，因此需要一种选择机制，从一组训练良好的生成模型中组合出单个模型。这类选择任务通常通过找出能使基于生成数据多样性与质量的评估分数最大化的模型来完成。然而，这种“最佳模型识别”方法忽略了一种可能性：现有模型的混合体表现可能优于每个单独模型。在本研究中，我们通过数值实验证明，在基准图像数据集上，生成模型的混合体相比单个模型确实能获得更优的评估分数（基于FID和KID分数）。这一发现推动了用于选择最优模型混合体的高效算法的开发。为解决该问题，我们构建了一个二次优化问题，以找到能使基于核的评估分数（包括核 inception 距离（KID）和Rényi核熵（RKE））达到最大值的最优混合模型。为了用尽可能少的样本查询确定最优模型混合体，我们将该选择任务建模为多臂老虎机（MAB）问题，并提出了Mixture Upper Confidence Bound（Mixture-UCB，混合上置信界）算法，该算法可证明能收敛至所涉模型的最优混合体。更广泛地说，所提出的Mixture-UCB算法可扩展用于优化一般MAB场景下混合权重的任意凸二次函数。我们证明了Mixture-UCB算法的遗憾界，并通过多项数值实验验证了该算法在文本与图像生成模型最优混合体寻找任务中的有效性。项目代码可在https://github.com/Rezaei-Parham/Mixture-UCB获取。
英文摘要：
The availability of multiple training algorithms and architectures for generative models requires a selection mechanism to form a single model over a group of well-trained generation models. The selection task is commonly addressed by identifying the model that maximizes an evaluation score based on the diversity and quality of the generated data. However, such a best-model identification approach overlooks the possibility that a mixture of available models can outperform each individual model. In this work, we numerically show that a mixture of generative models on benchmark image datasets can indeed achieve a better evaluation score (based on FID and KID scores), compared to the individual models. This observation motivates the development of efficient algorithms for selecting the optimal mixture of the models. To address this, we formulate a quadratic optimization problem to find an optimal mixture model achieving the maximum of kernel-based evaluation scores including kernel inception distance (KID) and Rényi kernel entropy (RKE). To identify the optimal mixture of the models using the fewest possible sample queries, we view the selection task as a multi-armed bandit (MAB) problem and propose the Mixture Upper Confidence Bound (Mixture-UCB) algorithm that provably converges to the optimal mixture of the involved models. More broadly, the proposed Mixture-UCB can be extended to optimize every convex quadratic function of the mixture weights in a general MAB setting. We prove a regret bound for the Mixture-UCB algorithm and perform several numerical experiments to show the success of Mixture-UCB in finding the optimal mixture of text and image generative models. The project code is available at https://github.com/Rezaei-Parham/Mixture-UCB.
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。
