Corpus ID: 221640862

On polynomial-time computation of high-dimensional posterior measures by Langevin-type algorithms

@article{Nickl2020OnPC,
  title={On polynomial-time computation of high-dimensional posterior measures by Langevin-type algorithms},
  author={R. Nickl and Sven Wang},
  journal={ArXiv},
  year={2020},
  volume={abs/2009.05298}
}
The problem of generating random samples of high-dimensional posterior distributions is considered. The main results consist of non-asymptotic computational guarantees for Langevin-type MCMC algorithms which scale polynomially in key quantities such as the dimension of the model, the desired precision level, and the number of available statistical measurements. As a direct consequence, it is shown that posterior mean vectors as well as optimisation based maximum a posteriori (MAP) estimates are… Expand
3 Citations

References

SHOWING 1-10 OF 83 REFERENCES
On the Computational Complexity of MCMC-based Estimators in Large Samples
  • 50
  • Highly Influential
  • PDF
Theoretical guarantees for approximate sampling from smooth and log‐concave densities
  • 226
  • Highly Influential
  • PDF
On the Computational Complexity of High-Dimensional Bayesian Variable Selection
  • 81
  • PDF
The geometry of logconcave functions and sampling algorithms
  • 146
  • PDF
Rates of contraction of posterior distributions based on Gaussian process priors
  • 315
  • PDF
Bayesian inverse problems for functions and applications to fluid mechanics
  • 128
  • PDF
Sampling can be faster than optimization
  • 44
  • PDF
Spectral gaps for a Metropolis–Hastings algorithm in infinite dimensions
  • 110
  • Highly Influential
  • PDF
Fundamentals of Nonparametric Bayesian Inference
  • 217
...
1
2
3
4
5
...