Stefano Ermon, Andy Shih, Dorsa Sadigh
We lifted 2 functions out of this paper's own repositories and ran 0 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 |
|---|---|---|
| andyshih12/hyperspn | alias | 0 of 2 |
| Function | Status | Where it lives |
|---|---|---|
| BaseSPN | Not yet run | andyshih12/hyperspn/hyperspn/HyperSPN.py pointer only (licence: NONE) · get_code("60c9f59a6f216d50") |
| HyperSPN | Not yet run | andyshih12/hyperspn/hyperspn/HyperSPN.py pointer only (licence: NONE) · get_code("4c5f82966652d6cb") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Probabilistic circuits (PCs) are a family of generative models which allows for the computation of exact likelihoods and marginals of its probability distributions. PCs are both expressive and tractable, and serve as popular choices for discrete density estimation tasks. However, large PCs are susceptible to overfitting, and only a few regularization strategies (e.g., dropout, weight-decay) have been explored. We propose HyperSPNs: a new paradigm of generating the mixture weights of large PCs using a small-scale neural network. Our framework can be viewed as a soft weight-sharing strategy, which combines the greater expressiveness of large models with the better generalization and memory-footprint properties of small models. We show the merits of our regularization strategy on two state-of-theart PC families introduced in recent literature -RAT-SPNs and EiNETs -and demonstrate generalization improvements in both models on a suite of density estimation benchmarks in both discrete and continuous domains. 35th Conference on Neural Information Processing Systems (NeurIPS 2021).
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2112.00914")
get_code_for_paper("2112.00914")
have("2112.00914")
Connect an agent — have() is free.