Gilles Louppe, François Rozet
We lifted 10 functions out of this paper's own repositories and ran 5 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 |
|---|---|---|
| francois-rozet/amnre | canonical | 5 of 10 |
| Function | Status | Where it lives |
|---|---|---|
| BatchNorm | Ran | francois-rozet/amnre/amnre/models.py code served (permissive licence) · get_code("4a85bc120f1fe8ba") |
| HyperNet | Ran | francois-rozet/amnre/amnre/models.py code served (permissive licence) · get_code("f4bedbc34fedea55") |
| MLP | Ran | francois-rozet/amnre/amnre/models.py code served (permissive licence) · get_code("d125701360b2c15c") |
| UnitNorm | Ran | francois-rozet/amnre/amnre/models.py code served (permissive licence) · get_code("750a98c20cc747f8") |
| reparametrize | Ran | francois-rozet/amnre/amnre/models.py code served (permissive licence) · get_code("ee91d0d3814c9f6e") |
| AMNRE | Not yet run | francois-rozet/amnre/amnre/models.py code served (permissive licence) · get_code("cbd5b622ccee6f42") |
| NRE | Not yet run | francois-rozet/amnre/amnre/models.py code served (permissive licence) · get_code("5df4d2274315178f") |
| ResBlock | Not yet run | francois-rozet/amnre/amnre/models.py code served (permissive licence) · get_code("902e1441da5f1fa6") |
| ResNet | Not yet run | francois-rozet/amnre/amnre/models.py code served (permissive licence) · get_code("e7c87e82b4676a1c") |
| lecun_init | Not yet run | francois-rozet/amnre/amnre/models.py code served (permissive licence) · get_code("3882391db97afb68") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
In many areas of science, complex phenomena are modeled by stochastic parametric simulators, often featuring high-dimensional parameter spaces and intractable likelihoods. In this context, performing Bayesian inference can be challenging. In this work, we present a novel method that enables amortized inference over arbitrary subsets of the parameters, without resorting to numerical integration, which makes interpretation of the posterior more convenient. Our method is efficient and can be implemented with arbitrary neural network architectures. We demonstrate the applicability of the method on parameter inference of binary black hole systems from gravitational waves observations.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2110.00449")
get_code_for_paper("2110.00449")
have("2110.00449")
Connect an agent — have() is free.