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.
Stochastic Gradient Langevin Dynamics infuses isotropic gradient noise to SGD to help navigate pathological curvature in the loss landscape for deep networks. Isotropic nature of the noise leads to poor scaling, and adaptive methods based on higher order curvature information such as Fisher Scoring have been proposed to precondition the noise in order to achieve better convergence. In this paper, we describe an adaptive method to estimate the parameters of the noise and conduct experiments on well-known model architectures to show that the adaptively preconditioned SGLD method achieves convergence with the speed of adaptive first order methods such as Adam, AdaGrad etc. and achieves generalization equivalent of SGD in the test set.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1906.04324")
get_code_for_paper("1906.04324")
have("1906.04324")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/1906.04324.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/1906.04324)
Connect an agent — have() is free.