SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1911.09189 · 2019

Information in Infinite Ensembles of Infinitely-Wide Neural Networks

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 5 functions out of this paper's own repositories and ran 3 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.

RepositoryRoleRan
ravidziv/info_ntk pwc_unofficial 3 of 5
FunctionStatusWhere it lives
onehot_encode Ran ravidziv/info_ntk/info_ntk/datasets.py
code served (permissive licence) · get_code("5769dceb172581d7")
process Ran ravidziv/info_ntk/info_ntk/datasets.py
code served (permissive licence) · get_code("d10f074d00b7bbdf")
reorder_dict Ran ravidziv/info_ntk/info_ntk/utils.py
code served (permissive licence) · get_code("eb172501670553f9")
create_df Not yet run ravidziv/info_ntk/info_ntk/utils.py
code served (permissive licence) · get_code("02a1224166a60380")
get_gibbs_loss Not yet run ravidziv/info_ntk/info_ntk/metrics.py
code served (permissive licence) · get_code("d71811ddab88406d")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In this preliminary work, we study the generalization properties of infinite ensembles of infinitely-wide neural networks. Amazingly, this model family admits tractable calculations for many information-theoretic quantities. We report analytical and empirical investigations in the search for signals that correlate with generalization.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1911.09189")
get_code_for_paper("1911.09189")
have("1911.09189")

Connect an agent — have() is free.