(Kernelized) Stein variational gradient descent

KSVD, SVGD

November 2, 2022 — January 9, 2023

Figure 1

Stein’s method meets variational inference via kernels and probability measures. The result is method of inference which maintains an ensemble of particles which notionally collectively sample from some target distribution. I should learn about this, as one of the methods I might use for low-assumption Bayes inference.

Let us examine the computable kernelized Stein discrepancy, invented in Q. Liu, Lee, and Jordan (2016), weaponized in Q. Liu, Lee, and Jordan (2016) and summarised in Xu and Matsuda (2021):

Let \(q\) be a smooth probability density on \(\mathbb{R}^{d} .\) For a smooth function \(\mathbf{f}=\) \(\left(f_{1}, \ldots, f_{d}\right): \mathbb{R}^{d} \rightarrow \mathbb{R}^{d}\), the Stein operator \(\mathcal{T}_{q}\) is defined by \[ \mathcal{T}_{q} \mathbf{f}(x)=\sum_{i=1}^{d}\left(f_{i}(x) \frac{\partial}{\partial x^{i}} \log q(x)+\frac{\partial}{\partial x^{i}} f_{i}(x)\right) \]

…Let \(\mathcal{H}\) be a reproducing kernel Hilbert space \((\mathrm{RKHS})\) on \(\mathbb{R}^{d}\) and \(\mathcal{H}^{d}\) be its product. By using Stein operator, kernel Stein discrepancy (KSD) (Gorham and Mackey 2015; Ley, Reinert, and Swan 2017) between two densities \(p\) and \(q\) is defined as \[ \operatorname{KSD}(p \| q)=\sup _{\|\mathbf{f}\|_{\mathcal{H}} \leq 1} \mathbb{E}_{p}\left[\mathcal{T}_{q} \mathbf{f}\right] \] It is shown that \(\operatorname{KSD}(p \| q) \geq 0\) and \(\mathrm{KSD}(p \| q)=0\) if and only if \(p=q\) under mild regularity conditions (Chwialkowski, Strathmann, and Gretton 2016). Thus, KSD is a proper discrepancy measure between densities. After some calculation, \(\operatorname{KSD}(p \| q)\) is rewritten as \[ \operatorname{KSD}^{2}(p \| q)=\mathbb{E}_{x, \tilde{x} \sim p}\left[h_{q}(x, \tilde{x})\right] \] where \(h_{q}\) does not involve \(p\).

TBD.

1 Moment matching interpretation

2 Incoming

3 References

Alsup, Venturi, and Peherstorfer. 2022. Multilevel Stein Variational Gradient Descent with Applications to Bayesian Inverse Problems.” In Proceedings of the 2nd Mathematical and Scientific Machine Learning Conference.
Ambrogioni, Güçlü, Güçlütürk, et al. 2018. Wasserstein Variational Inference.” In Proceedings of the 32Nd International Conference on Neural Information Processing Systems. NIPS’18.
Anastasiou, Barp, Briol, et al. 2022. Stein’s Method Meets Computational Statistics: A Review of Some Recent Developments.”
Chen, Wu, Chen, et al. 2020. Projected Stein Variational Newton: A Fast and Scalable Bayesian Inference Method in High Dimensions.”
Chu, Minami, and Fukumizu. 2022. The Equivalence Between Stein Variational Gradient Descent and Black-Box Variational Inference.” In.
Chwialkowski, Strathmann, and Gretton. 2016. A Kernel Test of Goodness of Fit.” In Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48. ICML’16.
Detommaso, Cui, Spantini, et al. 2018. A Stein Variational Newton Method.” In Proceedings of the 32nd International Conference on Neural Information Processing Systems. NIPS’18.
Detommaso, Hoitzing, Cui, et al. 2019. Stein Variational Online Changepoint Detection with Applications to Hawkes Processes and Neural Networks.” arXiv:1901.07987 [Cs, Stat].
Feng, Wang, and Liu. 2017. Learning to Draw Samples with Amortized Stein Variational Gradient Descent.” In UAI 2017.
Gong, Peng, and Liu. 2019. Quantile Stein Variational Gradient Descent for Batch Bayesian Optimization.” In Proceedings of the 36th International Conference on Machine Learning.
Gorham, and Mackey. 2015. Measuring Sample Quality with Stein’s Method.” In Advances in Neural Information Processing Systems.
Gorham, Raj, and Mackey. 2020. Stochastic Stein Discrepancies.” arXiv:2007.02857 [Cs, Math, Stat].
Han, and Liu. 2018. Stein Variational Gradient Descent Without Gradient.” In Proceedings of the 35th International Conference on Machine Learning.
Huggins, Campbell, Kasprzak, et al. 2018. Scalable Gaussian Process Inference with Finite-Data Mean and Variance Guarantees.” arXiv:1806.10234 [Cs, Stat].
Ley, Reinert, and Swan. 2017. Stein’s Method for Comparison of Univariate Distributions.” Probability Surveys.
Liu, Qiang. 2016. Stein Variational Gradient Descent: Theory and Applications.”
———. 2017. Stein Variational Gradient Descent as Gradient Flow.”
Liu, Qiang, Lee, and Jordan. 2016. A Kernelized Stein Discrepancy for Goodness-of-Fit Tests.” In Proceedings of The 33rd International Conference on Machine Learning.
Liu, Qiang, and Wang. 2018. Stein Variational Gradient Descent as Moment Matching.” In Proceedings of the 32nd International Conference on Neural Information Processing Systems. NIPS’18.
———. 2019. Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm.” In Advances In Neural Information Processing Systems.
Liu, Chang, and Zhu. 2018. Riemannian Stein Variational Gradient Descent for Bayesian Inference.” Proceedings of the AAAI Conference on Artificial Intelligence.
Liu, Xing, Zhu, Ton, et al. 2022. Grassmann Stein Variational Gradient Descent.” In Proceedings of The 25th International Conference on Artificial Intelligence and Statistics.
Pielok, Bischl, and Rügamer. 2023. Approximate Bayesian Inference with Stein Functional Variational Gradient Descent.” In.
Pulido, and van Leeuwen. 2019. Sequential Monte Carlo with Kernel Embedded Mappings: The Mapping Particle Filter.” Journal of Computational Physics.
Pulido, Van Leeuwen, and Posselt. 2019. Kernel Embedded Nonlinear Observational Mappings in the Variational Mapping Particle Filter.” In Computational Science – ICCS 2019. ICCS 2019. Lecture Notes in Computer Science.
Stordal, Moraes, Raanes, et al. 2021. P-Kernel Stein Variational Gradient Descent for Data Assimilation and History Matching.” Mathematical Geosciences.
Tamang, Ebtehaj, van Leeuwen, et al. 2021. Ensemble Riemannian Data Assimilation over the Wasserstein Space.” Nonlinear Processes in Geophysics.
Wang, Dilin, and Liu. 2019. Nonlinear Stein Variational Gradient Descent for Learning Diversified Mixture Models.” In Proceedings of the 36th International Conference on Machine Learning.
Wang, Ziyu, Ren, Zhu, et al. 2018. Function Space Particle Optimization for Bayesian Neural Networks.” In.
Wang, Dilin, Tang, Bajaj, et al. 2019. Stein Variational Gradient Descent with Matrix-Valued Kernels.” In Proceedings of the 33rd International Conference on Neural Information Processing Systems.
Wang, Dilin, Zeng, and Liu. 2018. Stein Variational Message Passing for Continuous Graphical Models.”
Wen, and Li. 2022. Affine-Mapping Based Variational Ensemble Kalman Filter.” Statistics and Computing.
Xu, and Matsuda. 2021. Interpretable Stein Goodness-of-Fit Tests on Riemannian Manifolds.” arXiv:2103.00895 [Stat].
Zhang, Zhang, Carin, et al. 2020. Stochastic Particle-Optimization Sampling and the Non-Asymptotic Convergence Theory.” In International Conference on Artificial Intelligence and Statistics.
Zhuo, Liu, Shi, et al. 2018. Message Passing Stein Variational Gradient Descent.” In Proceedings of the 35th International Conference on Machine Learning.