We lifted 9 functions out of this paper's own repositories and ran 4 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 |
|---|---|---|
| karlnapf/kernel_goodness_of_fit | canonical | 4 of 9 |
| Function | Status | Where it lives |
|---|---|---|
| grad_log_dens | Ran | karlnapf/kernel_goodness_of_fit/2dimNormal/2dimNormal.py code served (permissive licence) · get_code("70fb339d83a7c1bb") |
| logg | Ran | karlnapf/kernel_goodness_of_fit/2dimNormal/2dimNormal.py code served (permissive licence) · get_code("e4354ae81ee91ddc") |
| simulate | Ran | karlnapf/kernel_goodness_of_fit/stat_test/ar.py code served (permissive licence) · get_code("1f7f79604d019ecc") |
| simulatepm | Ran | karlnapf/kernel_goodness_of_fit/stat_test/ar.py code served (permissive licence) · get_code("592b744c9e05ee29") |
| SGLD | Not yet run | karlnapf/kernel_goodness_of_fit/sgld_test/bimodal_SGLD.py code served (permissive licence) · get_code("26b5447d97de57ad") |
| approximate_MH_accept | Not yet run | karlnapf/kernel_goodness_of_fit/samplers/austerity.py code served (permissive licence) · get_code("a1e3a4b16545a1c2") |
| austerity | Not yet run | karlnapf/kernel_goodness_of_fit/samplers/austerity.py code served (permissive licence) · get_code("6b7168e28268b01c") |
| evSGLD | Not yet run | karlnapf/kernel_goodness_of_fit/sgld_test/bimodal_SGLD.py code served (permissive licence) · get_code("a48418d972eb4746") |
| metropolis_hastings | Not yet run | karlnapf/kernel_goodness_of_fit/samplers/MetropolisHastings.py code served (permissive licence) · get_code("e7070853af855d53") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We propose a nonparametric statistical test for goodness-of-fit: given a set of samples, the test determines how likely it is that these were generated from a target density function. The measure of goodness-of-fit is a divergence constructed via Stein's method using functions from a Reproducing Kernel Hilbert Space. Our test statistic is based on an empirical estimate of this divergence, taking the form of a V-statistic in terms of the log gradients of the target density and the kernel. We derive a statistical test, both for i.i.d. and non-i.i.d. samples, where we estimate the null distribution quantiles using a wild bootstrap procedure. We apply our test to quantifying convergence of approximate Markov Chain Monte Carlo methods, statistical model criticism, and evaluating quality of fit vs model complexity in nonparametric density estimation.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1602.02964")
get_code_for_paper("1602.02964")
have("1602.02964")
Connect an agent — have() is free.