paper-with-me

Papers

Unbiased MLMC stochastic gradient-based optimization of Bayesian experimental designs

2020-05-18 · Takashi Goda, Tomohiko Hironaka, Wataru Kitade, Adam Foster

In this paper we propose an efficient stochastic optimization algorithm to search for Bayesian experimental designs such that the expected information gain is maximized. The gradient of the expected information gain with respect to experimental design parameters is given by a nested expectation, for which the standard Monte Carlo method using a fixed number of inner samples yields a biased estimator. In this paper, applying the idea of randomized multilevel Monte Carlo (MLMC) methods, we introduce an unbiased Monte Carlo estimator for the gradient of the expected information gain with finite expected squared $\ell_2$-norm and finite expected computational cost per sample. Our unbiased estimator can be combined well with stochastic gradient descent algorithms, which results in our proposal of an optimization algorithm to search for an optimal Bayesian experimental design. Numerical experiments confirm that our proposed algorithm works well not only for a simple test problem but also for a more realistic pharmacokinetic problem.

📄 PDF Abstract BibTeX arXiv:2005.08414

Code (1)

Goda-Research-Group/MLMC_stochastic_gradient 공식 구현

Tasks

Experimental DesignStochastic Optimization

Similar Papers 제목 키워드 기반

Efficient Debiased Evidence Estimation by Multilevel Monte Carlo Sampling

2020-01-14 · Kei Ishikawa, Takashi Goda

In this paper, we propose a new stochastic optimization algorithm for Bayesian inference based on multilevel Monte Carlo (MLMC) methods. In Bayesian statistics, biased estimators of the model evidence have been often use…

Bayesian InferenceStochastic Optimization

Multi-level Monte-Carlo Gradient Methods for Stochastic Optimization with Biased Oracles

2024-08-20 · Yifan Hu, Jie Wang, Xin Chen, Niao He

We consider stochastic optimization when one only has access to biased stochastic oracles of the objective and the gradient, and obtaining stochastic gradients with low biases comes at high costs. This setting captures v…

Contrastive LearningSchedulingStochastic Optimization

On the Bias-Variance-Cost Tradeoff of Stochastic Optimization

2021-12-01 · NeurIPS 2021 12 · Yifan Hu, Xin Chen, Niao He

We consider stochastic optimization when one only has access to biased stochastic oracles of the objective, and obtaining stochastic gradients with low biases comes at high costs. This setting captures a variety of optim…

Bilevel OptimizationStochastic Optimization

On the Parallel Complexity of Multilevel Monte Carlo in Stochastic Gradient Descent

2023-10-03 · Kei Ishikawa

In the stochastic gradient descent (SGD) for sequential simulations such as the neural stochastic differential equations, the Multilevel Monte Carlo (MLMC) method is known to offer better theoretical computational comple…

Smoothed Gradients for Stochastic Variational Inference

2014-06-13 · NeurIPS 2014 12 · Stephan Mandt, David Blei

Stochastic variational inference (SVI) lets us scale up Bayesian computation to massive data. It uses stochastic optimization to fit a variational distribution, following easy-to-compute noisy natural gradients. As with …

Stochastic OptimizationVariational Inference