Replication Data for: On the Universality of the Double Descent Peak in Ridgeless Regression (ICPSR doi:10.18419/darus-1771)

View:

Part 1: Document Description
Part 2: Study Description
Part 5: Other Study-Related Materials
Entire Codebook

(external link)

Document Description

Citation

Title:

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

Identification Number:

doi:10.18419/darus-1771

Distributor:

DaRUS

Date of Distribution:

2021-03-23

Version:

1

Bibliographic Citation:

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

Study Description

Citation

Title:

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

Identification Number:

doi:10.18419/darus-1771

Authoring Entity:

Holzmüller, David (Universität Stuttgart)

Grant Number:

EXC 2075 - 390740016

Distributor:

DaRUS

Access Authority:

Holzmüller, David

Access Authority:

Holzmüller, David

Access Authority:

Steinwart, Ingo

Depositor:

Holzmüller, David

Date of Deposit:

2021-03-16

Study Scope

Keywords:

Computer and Information Science, Mathematical Sciences

Abstract:

This dataset contains code used to generate the figures in the paper <em>On the Universality of the Double Descent Peak in Ridgeless Regression, David Holzmüller, International Conference on Learning Representations 2021</em>. The code is also provided on <a href=https://github.com/dholzmueller/universal_double_descent>GitHub</a>. Here, we additionally provide the data that is generated by the code and that is required to generate the plots. To use this data, simply unpack the (large!) file <code>data.tar.gz</code> inside the folder where the Python files are located. If the data is not downloaded and unpacked, the code will automatically compute it, which can take about one day on a 6-core-CPU. Information on the code and used software can be found in the file README.md.

Methodology and Processing

Sources Statement

Data Access

Notes:

Licensed under the <a href="http://www.apache.org/licenses/LICENSE-2.0">Apache License, Version 2.0</a> (the "License"); Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See <a href="http://www.apache.org/licenses/LICENSE-2.0">the License</a> for the specific language governing permissions and limitations under the License.

Other Study Description Materials

Related Publications

Citation

Identification Number:

2010.01851

Bibliographic Citation:

David Holzmüller. On the Universality of the Double Descent Peak in Ridgeless Regression. International Conference on Learning Representations, 2021.

Other Study-Related Materials

Label:

computation.py

Notes:

text/x-python

Other Study-Related Materials

Label:

data.tar.gz

Text:

Data generated by running the code

Notes:

application/gzip

Other Study-Related Materials

Label:

main.py

Notes:

text/x-python

Other Study-Related Materials

Label:

plotting.py

Notes:

text/x-python

Other Study-Related Materials

Label:

README.md

Notes:

text/markdown

Other Study-Related Materials

Label:

sampling.py

Notes:

text/x-python

Other Study-Related Materials

Label:

utils.py

Notes:

text/x-python