Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
156 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Leveraging Nested MLMC for Sequential Neural Posterior Estimation with Intractable Likelihoods (2401.16776v1)

Published 30 Jan 2024 in stat.CO, cs.LG, and stat.ML

Abstract: Sequential neural posterior estimation (SNPE) techniques have been recently proposed for dealing with simulation-based models with intractable likelihoods. They are devoted to learning the posterior from adaptively proposed simulations using neural network-based conditional density estimators. As a SNPE technique, the automatic posterior transformation (APT) method proposed by Greenberg et al. (2019) performs notably and scales to high dimensional data. However, the APT method bears the computation of an expectation of the logarithm of an intractable normalizing constant, i.e., a nested expectation. Although atomic APT was proposed to solve this by discretizing the normalizing constant, it remains challenging to analyze the convergence of learning. In this paper, we propose a nested APT method to estimate the involved nested expectation instead. This facilitates establishing the convergence analysis. Since the nested estimators for the loss function and its gradient are biased, we make use of unbiased multi-level Monte Carlo (MLMC) estimators for debiasing. To further reduce the excessive variance of the unbiased estimators, this paper also develops some truncated MLMC estimators by taking account of the trade-off between the bias and the average cost. Numerical experiments for approximating complex posteriors with multimodal in moderate dimensions are provided.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (57)
  1. On the convergence of SGD with biased gradients. arXiv preprint arXiv:2008.00051.
  2. Particle Markov chain Monte Carlo methods. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 72(3):269–342.
  3. The pseudo-marginal approach for efficient Monte Carlo computations. The Annals of Statistics, 37(2):697 – 725.
  4. Adaptive approximate Bayesian computation. Biometrika, 96(4):983–990.
  5. Approximate Bayesian computation in population genetics. Genetics, 162(4):2025–2035.
  6. Optimization methods for large-scale machine learning. SIAM Review, 60(2):223–311.
  7. Mining gold from implicit models to improve likelihood-free inference. Proceedings of the National Academy of Sciences, 117(10):5242–5249.
  8. Multilevel simulation of functionals of bernoulli random variables with application to basket credit derivatives. Methodology and Computing in Applied Probability, 17:579–604.
  9. Nesterov-aided stochastic gradient methods using Laplace approximation for Bayesian design optimization. Computer Methods in Applied Mechanics and Engineering, 363:112909.
  10. The properties of high-dimensional data spaces: implications for exploring gene and protein expression data. Nature Reviews Cancer, 8(1):37–49.
  11. The frontier of simulation-based inference. Proceedings of the National Academy of Sciences, 117(48):30055–30062.
  12. Validation of approximate likelihood and emulator models for computationally intensive simulations. In International Conference on Artificial Intelligence and Statistics, pages 3349–3361. PMLR.
  13. Truncated proposals for scalable and hassle-free simulation-based inference. arXiv preprint arXiv:2210.04815.
  14. Neural spline flows. Advances in Neural Information Processing Systems, 32.
  15. Constructing summary statistics for approximate Bayesian computation: semi-automatic approximate Bayesian computation. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 74(3):419–474.
  16. Variational Bayesian optimal experimental design. Advances in Neural Information Processing Systems, 32.
  17. Giles, M. B. (2015). Multilevel Monte Carlo methods. Acta Numerica, 24:259–328.
  18. Giles, M. B. (2018). MLMC for nested expectations. In Contemporary Computational Mathematics-A Celebration of the 80th Birthday of Ian Sloan, pages 425–442.
  19. Decision-making under uncertainty: using MLMC for efficient estimation of EVPPI. Statistics and Computing, 29:739–751.
  20. Antithetic multilevel Monte Carlo estimation for multi-dimensional SDEs without Lévy area simulation. The Annals of Applied Probability, 24(4):1585 – 1620.
  21. Gillespie, D. T. (1977). Exact stochastic simulation of coupled chemical reactions. The Journal of Physical Chemistry, 81(25):2340–2361.
  22. Multilevel Monte Carlo estimation of expected information gains. Stochastic Analysis and Applications, 38(4):581–600.
  23. Unbiased MLMC stochastic gradient-based optimization of Bayesian experimental designs. SIAM Journal on Scientific Computing, 44(1):A286–A311.
  24. Training deep neural density estimators to identify mechanistic models of neural dynamics. Elife, 9:e56261.
  25. Automatic posterior transformation for likelihood-free inference. In International Conference on Machine Learning, pages 2404–2414. PMLR.
  26. A kernel two-sample test. The Journal of Machine Learning Research, 13(1):723–773.
  27. Bayesian optimization for likelihood-free inference of simulator-based statistical models. Journal of Machine Learning Research.
  28. Likelihood-free inference via classification. Statistics and Computing, 28:411–425.
  29. Amortized Bayesian inference on generative dynamical network models of epilepsy using deep neural density estimators. Neural Networks, 163:178–194.
  30. Unbiased MLMC-based variational Bayes for likelihood-free inference. SIAM Journal on Scientific Computing, 44(4):A1884–A1910.
  31. Likelihood-free MCMC with amortized approximate ratio estimators. In International conference on machine learning, pages 4239–4248. PMLR.
  32. A Trust Crisis In Simulation-Based Inference? Your Posterior Approximations Can Be Unfaithful. arXiv preprint arXiv:2110.06581.
  33. On the bias-variance-cost tradeoff of stochastic optimization. Advances in Neural Information Processing Systems, 34:22119–22131.
  34. Gradient-based stochastic optimization methods in Bayesian experimental design. International Journal for Uncertainty Quantification, 4(6).
  35. Unbiased Markov chain Monte Carlo with couplings. arXiv preprint arXiv:1708.03625.
  36. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
  37. Bayesian experimental design for implicit models by mutual information neural estimation. In International Conference on Machine Learning, pages 5316–5326. PMLR.
  38. Normalizing flows: An introduction and review of current methods. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(11):3964–3979.
  39. Biological factors controlling starch digestibility in human digestive system. Food Science and Human Wellness, 12(2):351–358.
  40. Revisiting classifier two-sample tests. arXiv preprint arXiv:1610.06545.
  41. Benchmarking simulation-based inference. In International Conference on Artificial Intelligence and Statistics, pages 343–351. PMLR.
  42. Flexible statistical inference for mechanistic models of neural dynamics. Advances in Neural Information Processing Systems, 30.
  43. Sumo: Unbiased estimation of log marginal probability for latent variable models. In International Conference on Learning Representations.
  44. On Russian roulette estimates for Bayesian inference with doubly-intractable likelihoods. Statistical Science, 30(4).
  45. Approximate Bayesian computational methods. Statistics and Computing, 22(6):1167–1180.
  46. Systems Biology and Cell Signaling: A Comprehensive Review. Asian Journal of Basic and Applied Sciences, 10(06-2023).
  47. Neural data science: accelerating the experiment-analysis-theory cycle in large-scale neuroscience. Current Opinion in Neurobiology, 50:232–241.
  48. Fast ε𝜀\varepsilonitalic_ε-free inference of simulation models with Bayesian conditional density estimation. Advances in Neural Information Processing Systems, 29.
  49. Sequential neural likelihood: Fast likelihood-free inference with autoregressive flows. In The 22nd International Conference on Artificial Intelligence and Statistics, pages 837–848. PMLR.
  50. Bayesian synthetic likelihood. Journal of Computational and Graphical Statistics, 27(1):1–11.
  51. Unbiased estimation with square root convergence for SDE models. Operations Research, 63(5):1026–1043.
  52. Vision-as-inverse-graphics: Obtaining a rich 3d explanation of a scene from a single image. In Proceedings of the IEEE International Conference on Computer Vision Workshops, pages 851–859.
  53. Ryan, K. J. (2003). Estimating expected information gains for experimental designs with application to the random fatigue-limit model. Journal of Computational and Graphical Statistics, 12(3):585–603.
  54. On Bayesian inference for the M/G/1 queue with efficient MCMC sampling. arXiv preprint arXiv:1401.5548.
  55. Likelihood-free inference by ratio estimation. Bayesian Analysis, 17(1):1–31.
  56. Variational Bayes with intractable likelihood. Journal of Computational and Graphical Statistics, 26(4):873–882.
  57. Wood, S. N. (2010). Statistical inference for noisy nonlinear ecological dynamic systems. Nature, 466(7310):1102–1104.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now