The generator gradient estimator is an adjoint state method for stochastic differential equations
Motivated by the increasing popularity of overparameterized Stochastic Differential Equations (SDEs) like Neural SDEs, Wang, Blanchet and Glynn recently introduced the generator gradient estimator, a novel unbiased stochastic gradient estimator for SDEs whose computation time remains stable in the number of parameters. In this note, we demonstrate that this estimator is in fact an adjoint state method, an approach which is known to scale with the number of states and not the number of parameters in the case of Ordinary Differential Equations (ODEs). In addition, we show that the generator gradient estimator is a close analogue to the exact Integral Path Algorithm (eIPA) estimator which was introduced by Gupta, Rathinam and Khammash for a class of Continuous-Time Markov Chains (CTMCs) known as stochastic chemical reactions networks (CRNs).
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Scalable Gradients and Variational Inference for Stochastic Differential Equations
We derive reverse-mode (or adjoint) automatic differentiation for solutions of stochastic differential equations (SDEs), allowing time-efficient and constant-memory computation of pathwise gradients, a continuous-time an…
Time SeriesTime Series AnalysisVariational InferenceInexact bilevel stochastic gradient methods for constrained and unconstrained lower-level problems
Two-level stochastic optimization formulations have become instrumental in a number of machine learning contexts such as continual learning, neural architecture search, adversarial learning, and hyperparameter tuning. Pr…
BIG-bench Machine LearningBilevel OptimizationContinual LearningNeural Architecture Search+1Efficient Adjoint Matching for Fine-tuning Diffusion Models
Reward fine-tuning has become a common approach for aligning pretrained diffusion and flow models with human preferences in text-to-image generation. Among reward-gradient-based methods, Adjoint Matching (AM) provides a …
Text-to-Image GenerationA Unified Theory of $θ$-Expectations
We derive a new class of non-linear expectations from first-principles deterministic chaotic dynamics. The homogenization of the system's skew-adjoint microscopic generator is achieved using the spectral theory of transf…
A stochastic gradient method for trilevel optimization
With the success that the field of bilevel optimization has seen in recent years, similar methodologies have started being applied to solving more difficult applications that arise in trilevel optimization. At the helm o…
Bilevel Optimization