Importance Sampling

By Mevin B. Hooten, T. Hefley. 2019

Subfields: Probabilistic & Bayesian Methods

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Probabilistic & Bayesian Methods

Citations in the corpus

On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting (2022, background): “…= a(x)e Pn i=1 i i(x), (16) where i terms control the moments µi of the associated features, which can be estimated through self-normalized importance sampling (Owen, 2013); and then, to make the moments match the desired values, the i terms can be optimized through SGD (Parshakova et al., 2019a).”
Learning When-to-Treat Policies (2019, methodology): “Inverse-propensity type methods, including outcome-weighted learning and importance sampling, are transparent and simple to implement; however, they have sometimes been observed exhibit problematically high variance, especially in dynamic settings (see, e.g., Doroudi, Thomas, and Brunskill 2017).”
A Distributional Approach to Controlled Text Generation (2020, methodology): “…an ablation experiments with both metrics (Appendix 2) Given P and a proposal distribution q that we can sample from, using importance sampling (Owen, 2013), one can calculate the partition function Z as follows: Z = ∑ x P (x) = ∑ x q(x) P (x)/q(x) = Ex∼q(x) P (x)/q(x) (7) We can then compute…”
Energy-Based Models for Code Generation under Compilability Constraints (2021, background): “The gradient of this KL turns out to be tractable: Let us now absorb the constant − 1 /Z into a learning rate α ( θ ) and estimate the expectation over p ( x ) using importance sampling (Owen, 2013) from yet another generative model q : During training, both π θ and q are initialized as a .”
An approximate sampler for energy-based models with divergence diagnostics (2022, methodology): “The vector λ is found using self-normalized importance sampling (Owen, 2013; Parshakova et al., 2019a) and stochastic optimization.”
Survey of multifidelity methods in uncertainty propagation, inference, and optimization (2018, background): “3 Multifidelity uncertainty propagation based on importance sampling Importance sampling [79, 177, 192] uses a problem-dependent sampling strategy.”