Simon Carbonnelle, Christophe De Vleeschouwer
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.
Several works have shown that the regularization mechanisms underlying deep neural networks' generalization performances are still poorly understood (Neyshabur et al., 2015;Zhang et al., 2017). In this paper, we hypothesize that deep neural networks are regularized through their ability to extract meaningful clusters among the samples of a class. This constitutes an implicit form of regularization, as no explicit training mechanisms or supervision target such behaviour. To support our hypothesis, we design four different measures of intraclass clustering, based on the neuron-and layer-level representations of the training data. We then show that these measures constitute accurate predictors of generalization performance across variations of a large set of hyperparameters (learning rate, batch size, optimizer, weight decay, dropout rate, data augmentation, network depth and width).
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2103.06733")
get_code_for_paper("2103.06733")
have("2103.06733")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2103.06733.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2103.06733)
Connect an agent — have() is free.