We lifted 3 functions out of this paper's own repositories and ran 3 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| Ending2015a/toy_gradlogp | reimplementation | 3 of 3 |
| Function | Status | Where it lives |
|---|---|---|
| anneal_langevin_dynamics | Ran | Ending2015a/toy_gradlogp/toy_gradlogp/utils.py code served (permissive licence) · get_code("9d5b84ff88fd1554") |
| langevin_dynamics | Ran | Ending2015a/toy_gradlogp/toy_gradlogp/utils.py code served (permissive licence) · get_code("0e2fe8d41e723fb9") |
| sample_score_field | Ran | Ending2015a/toy_gradlogp/toy_gradlogp/utils.py code served (permissive licence) · get_code("69056e76ee50c6a6") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Energy-Based Models (EBMs), also known as non-normalized probabilistic models, specify probability density or mass functions up to an unknown normalizing constant. Unlike most other probabilistic models, EBMs do not place a restriction on the tractability of the normalizing constant, thus are more flexible to parameterize and can model a more expressive family of probability distributions. However, the unknown normalizing constant of EBMs makes training particularly difficult. Our goal is to provide a friendly introduction to modern approaches for EBM training. We start by explaining maximum likelihood training with Markov chain Monte Carlo (MCMC), and proceed to elaborate on MCMC-free approaches, including Score Matching (SM) and Noise Constrastive Estimation (NCE). We highlight theoretical connections among these three approaches, and end with a brief survey on alternative training methods, which are still under active research. Our tutorial is targeted at an audience with basic understanding of generative models who want to apply EBMs or start a research project in this direction.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2101.03288")
get_code_for_paper("2101.03288")
have("2101.03288")
Connect an agent — have() is free.