https://github.com/dholzmueller/sampling_experiments

Code for reproducing the plots in our paper "Convergence Rates for Non-Log-Concave Sampling and Log-Partition Estimation"
https://github.com/dholzmueller/sampling_experiments

Last synced: 24 days ago
JSON representation

Code for reproducing the plots in our paper "Convergence Rates for Non-Log-Concave Sampling and Log-Partition Estimation"

• Host: GitHub
• URL: https://github.com/dholzmueller/sampling_experiments
• Owner: dholzmueller
• License: apache-2.0
• Created: 2023-02-15T14:12:47.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2023-03-07T07:43:18.000Z (almost 2 years ago)
• Last Synced: 2024-05-20T19:53:18.292Z (7 months ago)
• Language: Python
• Size: 16.6 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
This Python Code can be used to reproduced the figures of our paper ["Convergence Rates for Non-Log-Concave Sampling and Log-Partition Estimation"](https://arxiv.org/abs/2303.03237). Please cite the paper if you use this code for research purposes. It requires the `torch`, `numpy` and `matplotlib` libraries to run. All figures will be generated by running `python3 experiments.py device`, where `device` can be a PyTorch device name like `cpu` or `cuda:0`. Intermediate results will be saved in order to avoid recomputing them if a plot should be changed.