We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We show that unconverged stochastic gradient descent can be interpreted as a procedure that samples from a nonparametric variational approximate posterior distribution. This distribution is implicitly defined as the transformation of an initial distribution by a sequence of optimization updates. By tracking the change in entropy over this sequence of transformations during optimization, we form a scalable, unbiased estimate of the variational lower bound on the log marginal likelihood. We can use this bound to optimize hyperparameters instead of using cross-validation. This Bayesian interpretation of SGD suggests improved, overfitting-resistant optimization procedures, and gives a theoretical foundation for popular tricks such as early stopping and ensembling. We investigate the properties of this marginal likelihood estimator on neural network models.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1504.01344")
get_code_for_paper("1504.01344")
have("1504.01344")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/1504.01344.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/1504.01344)
Connect an agent — have() is free.