We lifted 5 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 |
|---|---|---|
| Victorletzelter/VoronoiWTA | canonical | 5 of 5 |
| Function | Status | Where it lives |
|---|---|---|
| compute_accelerated_angular_distance | Ran | Victorletzelter/VoronoiWTA/audio/src/metrics.py pointer only (licence: NONE) · get_code("f8b3d7470c88c99e") |
| compute_spherical_distance_np | Ran | Victorletzelter/VoronoiWTA/audio/src/metrics.py pointer only (licence: NONE) · get_code("1df64f4a32962a3e") |
| create_cost_matrix | Ran | Victorletzelter/VoronoiWTA/audio/src/metrics.py pointer only (licence: NONE) · get_code("11a7e2c81f8a0420") |
| get_pylogger | Ran | Victorletzelter/VoronoiWTA/audio/src/utils/pylogger.py pointer only (licence: NONE) · get_code("aebb727eed75bd10") |
| wrap_to_spherical_coordinates | Ran | Victorletzelter/VoronoiWTA/audio/src/utils/utils.py pointer only (licence: NONE) · get_code("bd272d3cde62b8c8") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Winner-takes-all training is a simple learning paradigm, which handles ambiguous tasks by predicting a set of plausible hypotheses. Recently, a connection was established between Winner-takes-all training and centroidal Voronoi tessellations, showing that, once trained, hypotheses should quantize optimally the shape of the conditional distribution to predict. However, the best use of these hypotheses for uncertainty quantification is still an open question. In this work, we show how to leverage the appealing geometric properties of the Winner-takes-all learners for conditional density estimation, without modifying its original training scheme. We theoretically establish the advantages of our novel estimator both in terms of quantization and density estimation, and we demonstrate its competitiveness on synthetic and real-world datasets, including audio data.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2406.04706")
get_code_for_paper("2406.04706")
have("2406.04706")
Connect an agent — have() is free.