Poster
in
Workshop: Differentiable Almost Everything: Differentiable Relaxations, Algorithms, Operators, and Simulators
Implicit Diffusion: Efficient Optimization through Stochastic Sampling
Pierre Marion · Anna Korba · Peter Bartlett · Mathieu Blondel · Valentin De Bortoli · Arnaud Doucet · Felipe Llinares-Lopez · Courtney Paquette · Quentin Berthet
Keywords: [ Differentiation ] [ Diffusion ] [ sampling ] [ bilevel ]
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. We showcase it in training and finetuning applications.