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 |
|---|---|---|
| BennyAvelin/DeepLimitNeuralODE | canonical | 3 of 3 |
| copy not recorded | — | 2 of 2 |
| Function | Status | Where it lives |
|---|---|---|
| Embedding | Ran | this paper's copy was not recorded; identical code first harvested from instance-wise-ordered-transformer/iot pointer only · get_code("96cbb5e9ca5b6be0") |
| Linear | Ran | this paper's copy was not recorded; identical code first harvested from instance-wise-ordered-transformer/iot pointer only · get_code("8cd8cb0d1e9e63e4") |
| generate_data | Ran | BennyAvelin/DeepLimitNeuralODE/Annulus_crossval.py pointer only (licence: GPL-3.0) · get_code("cd9985cdef068208") |
| lr_schedule | Ran | BennyAvelin/DeepLimitNeuralODE/Annulus_crossval.py pointer only (licence: GPL-3.0) · get_code("fbb44bf5d58a7062") |
| lr_schedule | Ran | BennyAvelin/DeepLimitNeuralODE/Cifar10_crossval.py pointer only (licence: GPL-3.0) · get_code("e8e37a5dfe0ab695") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
In this paper we prove that, in the deep limit, the stochastic gradient descent on a ResNet type deep neural network, where each layer shares the same weight matrix, converges to the stochastic gradient descent for a Neural ODE and that the corresponding value/loss functions converge. Our result gives, in the context of minimization by stochastic gradient descent, a theoretical foundation for considering Neural ODEs as the deep limit of ResNets. Our proof is based on certain decay estimates for associated Fokker-Planck equations.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1906.12183")
get_code_for_paper("1906.12183")
have("1906.12183")
Connect an agent — have() is free.