隱式擴散：透過隨機抽樣實現高效優化

摘要

我們提出了一種優化分佈的新演算法，這些分佈是由帶有參數的隨機擴散隱式定義的。透過這種方式，我們能夠通過優化其參數來修改抽樣過程的結果分佈。我們引入了一個通用框架，用於對這些過程進行一階優化，該框架在單個循環中同時執行優化和抽樣步驟。這種方法受到雙層優化和自動隱式微分的最新進展的啟發，利用了將抽樣視為對概率分佈空間的優化的觀點。我們對我們方法的性能提供了理論保證，並通過實驗結果展示了它在現實世界環境中的有效性。

English

We present a new algorithm to optimize distributions defined implicitly by parameterized stochastic diffusions. Doing so allows us to modify the outcome distribution of sampling processes by optimizing over their parameters. We introduce a general framework for first-order optimization of these processes, that performs jointly, in a single loop, optimization and sampling steps. This approach is inspired by recent advances in bilevel optimization and automatic implicit differentiation, leveraging the point of view of sampling as optimization over the space of probability distributions. We provide theoretical guarantees on the performance of our method, as well as experimental results demonstrating its effectiveness in real-world settings.

隱式擴散：透過隨機抽樣實現高效優化

Implicit Diffusion: Efficient Optimization through Stochastic Sampling

摘要

Support