Stein Variational Evolution Strategies
This work addresses a bottleneck in gradient-free variational inference for researchers and practitioners in machine learning, though it is incremental as it builds on existing SVGD and ES techniques.
The paper tackled the problem of sampling from unnormalized probability distributions without gradient information by combining Stein Variational Gradient Descent with evolution strategy updates, resulting in significantly improved performance on challenging benchmarks compared to prior gradient-free methods.
Stein Variational Gradient Descent (SVGD) is a highly efficient method to sample from an unnormalized probability distribution. However, the SVGD update relies on gradients of the log-density, which may not always be available. Existing gradient-free versions of SVGD make use of simple Monte Carlo approximations or gradients from surrogate distributions, both with limitations. To improve gradient-free Stein variational inference, we combine SVGD steps with evolution strategy (ES) updates. Our results demonstrate that the resulting algorithm generates high-quality samples from unnormalized target densities without requiring gradient information. Compared to prior gradient-free SVGD methods, we find that the integration of the ES update in SVGD significantly improves the performance on multiple challenging benchmark problems.