We lifted 9 functions out of this paper's own repositories and ran 8 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 |
|---|---|---|
| albcab/mfm | canonical | 8 of 9 |
| Function | Status | Where it lives |
|---|---|---|
| create_learning_rate_fn | Ran | albcab/mfm/exe_flow_matching.py pointer only (licence: NONE) · get_code("9ff19b4076d60a34") |
| get_bin_counts | Ran | albcab/mfm/cox_process_utils.py pointer only (licence: NONE) · get_code("9303cdbe67021bf7") |
| get_bin_vals | Ran | albcab/mfm/cox_process_utils.py pointer only (licence: NONE) · get_code("af767a03e2037f30") |
| gram | Ran | albcab/mfm/cox_process_utils.py pointer only (licence: NONE) · get_code("1394231f7de85953") |
| inference_loop | Ran | albcab/mfm/mcmc_utils.py pointer only (licence: NONE) · get_code("8215d729b7afbd08") |
| linear_map | Ran | albcab/mfm/bblackjax/util.py pointer only (licence: NONE) · get_code("78c695bb394d4bf8") |
| optimize | Ran | albcab/mfm/bblackjax/adaptation/atess.py pointer only (licence: NONE) · get_code("8d5bcf8e0385793c") |
| stein_disc | Ran | albcab/mfm/mcmc_utils.py pointer only (licence: NONE) · get_code("e0b7c5e41c7f98e7") |
| inference_loop0 | Not yet run | albcab/mfm/mcmc_utils.py pointer only (licence: NONE) · get_code("b1982ee1cd473040") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Continuous normalizing flows (CNFs) learn the probability path between a reference distribution and a target distribution by modeling the vector field generating said path using neural networks. Recently, Lipman et al. (2022) introduced a simple and inexpensive method for training CNFs in generative modeling, termed flow matching (FM). In this paper, we repurpose this method for probabilistic inference by incorporating Markovian sampling methods in evaluating the FM objective, and using the learned CNF to improve Monte Carlo sampling. Specifically, we propose an adaptive Markov chain Monte Carlo (MCMC) algorithm, which combines a local Markov transition kernel with a non-local, flow-informed transition kernel, defined using a CNF. This CNF is adapted on-the-fly using samples from the Markov chain, which are used to specify the probability path for the FM objective. Our method also includes an adaptive tempering mechanism that allows the discovery of multiple modes in the target distribution. Under mild assumptions, we establish convergence of our method to a local optimum of the FM objective. We then benchmark our approach on several synthetic and real-world examples, achieving similar performance to other state-of-the-art methods, but often at a significantly lower computational cost.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2405.14392")
get_code_for_paper("2405.14392")
have("2405.14392")
Connect an agent — have() is free.