PN 6-3

SimTech Project PN6-3 "Understanding Physical Constraints in Machine Learning for Simulation"

Featured Dataverses

In order to use this feature you must have at least one published or linked dataverse.

Publish Dataverse

Are you sure you want to publish your dataverse? Once you do so it must remain published.

Publish Dataverse

This dataverse cannot be published because the dataverse it is in has not been published.

Delete Dataverse

Are you sure you want to delete your dataverse? You cannot undelete this dataverse.

11 to 20 of 27 Results

README.md Jun 20, 2022 - Code for: Training Two-Layer ReLU Networks with Gradient Descent is Inconsistent Markdown Text - 5.3 KB - MD5: 681760ae446fff1be139c4ff640fb034
requirements.txt Jun 20, 2022 - Code for: Training Two-Layer ReLU Networks with Gradient Descent is Inconsistent Plain Text - 637 B - MD5: 09b283d76024ec31e9134f8d4bf7636d
run_nn_setups.py Jun 20, 2022 - Code for: Training Two-Layer ReLU Networks with Gradient Descent is Inconsistent Python Source Code - 30.7 KB - MD5: ea8311dc8c3e079b3caa9a1c6774412a
show_training.py Jun 20, 2022 - Code for: Training Two-Layer ReLU Networks with Gradient Descent is Inconsistent Python Source Code - 17.1 KB - MD5: c0aeba6d65554d5395ca28296a781ea0
tex_head.txt Jun 20, 2022 - Code for: Training Two-Layer ReLU Networks with Gradient Descent is Inconsistent Plain Text - 4.9 KB - MD5: 4c5247ed7dab1c2c29f8e470d1dc271e
tex_tail.txt Jun 20, 2022 - Code for: Training Two-Layer ReLU Networks with Gradient Descent is Inconsistent Plain Text - 124 B - MD5: 47aeb495fcff06691708ae2515da5e49
TrainingSetup.py Jun 20, 2022 - Code for: Training Two-Layer ReLU Networks with Gradient Descent is Inconsistent Python Source Code - 11.2 KB - MD5: 73b9c67f5a7a2513bee4c2b93e33e34c
train_star_dataset.py Jun 20, 2022 - Code for: Training Two-Layer ReLU Networks with Gradient Descent is Inconsistent Python Source Code - 20.0 KB - MD5: 92dd31d212970c4a430d131855d5631d
utils.py Jun 20, 2022 - Code for: Training Two-Layer ReLU Networks with Gradient Descent is Inconsistent Python Source Code - 2.9 KB - MD5: 44757495ab97921515a4296648fed8a3
Replication Data for: On the Universality of the Double Descent Peak in Ridgeless Regression Mar 23, 2021 Holzmüller, David, 2021, "Replication Data for: On the Universality of the Double Descent Peak in Ridgeless Regression", https://doi.org/10.18419/darus-1771, DaRUS, V1 This dataset contains code used to generate the figures in the paper On the Universality of the Double Descent Peak in Ridgeless Regression, David Holzmüller, International Conference on Learning Representations 2021. The code is also provided on GitHub. Here, we additionally pro...

README.md

Jun 20, 2022 - Code for: Training Two-Layer ReLU Networks with Gradient Descent is Inconsistent

Markdown Text - 5.3 KB -

requirements.txt

Jun 20, 2022 - Code for: Training Two-Layer ReLU Networks with Gradient Descent is Inconsistent

Plain Text - 637 B -

run_nn_setups.py

Jun 20, 2022 - Code for: Training Two-Layer ReLU Networks with Gradient Descent is Inconsistent

Python Source Code - 30.7 KB -

show_training.py

Jun 20, 2022 - Code for: Training Two-Layer ReLU Networks with Gradient Descent is Inconsistent

Python Source Code - 17.1 KB -

tex_head.txt

Jun 20, 2022 - Code for: Training Two-Layer ReLU Networks with Gradient Descent is Inconsistent

Plain Text - 4.9 KB -

tex_tail.txt

Jun 20, 2022 - Code for: Training Two-Layer ReLU Networks with Gradient Descent is Inconsistent

Plain Text - 124 B -

TrainingSetup.py

Jun 20, 2022 - Code for: Training Two-Layer ReLU Networks with Gradient Descent is Inconsistent

Python Source Code - 11.2 KB -

train_star_dataset.py

Jun 20, 2022 - Code for: Training Two-Layer ReLU Networks with Gradient Descent is Inconsistent

Python Source Code - 20.0 KB -

utils.py

Jun 20, 2022 - Code for: Training Two-Layer ReLU Networks with Gradient Descent is Inconsistent

Python Source Code - 2.9 KB -

Replication Data for: On the Universality of the Double Descent Peak in Ridgeless Regression

Mar 23, 2021

Holzmüller, David, 2021, "Replication Data for: On the Universality of the Double Descent Peak in Ridgeless Regression", https://doi.org/10.18419/darus-1771, DaRUS, V1

This dataset contains code used to generate the figures in the paper On the Universality of the Double Descent Peak in Ridgeless Regression, David Holzmüller, International Conference on Learning Representations 2021. The code is also provided on GitHub. Here, we additionally pro...

Add Data

Share Dataverse

Link Dataverse

Reset Modifications