We lifted 1 functions out of this paper's own repositories and ran 1 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 |
|---|---|---|
| lzzcd001/ade-code | canonical | 1 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| eval_callback | Ran | lzzcd001/ade-code/ade/experiments/mvn_unimodal/main_ade.py pointer only (licence: NONE) · get_code("d711490f223e8e72") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We present an efficient algorithm for maximum likelihood estimation (MLE) of exponential family models, with a general parametrization of the energy function that includes neural networks. We exploit the primal-dual view of the MLE with a kinetics augmented model to obtain an estimate associated with an adversarial dual sampler. To represent this sampler, we introduce a novel neural architecture, dynamics embedding, that generalizes Hamiltonian Monte-Carlo (HMC). The proposed approach inherits the flexibility of HMC while enabling tractable entropy estimation for the augmented model. By learning both a dual sampler and the primal model simultaneously, and sharing parameters between them, we obviate the requirement to design a separate sampling procedure once the model has been trained, leading to more effective learning. We show that many existing estimators, such as contrastive divergence, pseudo/composite-likelihood, score matching, minimum Stein discrepancy estimator, non-local contrastive objectives, noise-contrastive estimation, and minimum probability flow, are special cases of the proposed approach, each expressed by a different (fixed) dual sampler. An empirical investigation shows that adapting the sampler during MLE can significantly improve on state-of-the-art estimators.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1904.12083")
get_code_for_paper("1904.12083")
have("1904.12083")
Connect an agent — have() is free.