Sascha Marton
@smarton.bsky.social
Machine Learning Researcher & PhD Candidate @ University of Mannheim
Reposted by Sascha Marton
PyTabKit 1.1 is out!
- Includes TabM and provides a scikit-learn interface
- some baseline NN parameter names are renamed (removed double-underscores)
- other small changes, see the readme.
github.com/dholzmueller...
- Includes TabM and provides a scikit-learn interface
- some baseline NN parameter names are renamed (removed double-underscores)
- other small changes, see the readme.
github.com/dholzmueller...
Can deep learning finally compete with boosted trees on tabular data? 🌲
In our NeurIPS 2024 paper, we introduce RealMLP, a NN with improvements in all areas and meta-learned default parameters.
Some insights about RealMLP and other models on large benchmarks (>200 datasets): 🧵
In our NeurIPS 2024 paper, we introduce RealMLP, a NN with improvements in all areas and meta-learned default parameters.
Some insights about RealMLP and other models on large benchmarks (>200 datasets): 🧵
November 25, 2024 at 10:49 AM
PyTabKit 1.1 is out!
- Includes TabM and provides a scikit-learn interface
- some baseline NN parameter names are renamed (removed double-underscores)
- other small changes, see the readme.
github.com/dholzmueller...
- Includes TabM and provides a scikit-learn interface
- some baseline NN parameter names are renamed (removed double-underscores)
- other small changes, see the readme.
github.com/dholzmueller...
Reposted by Sascha Marton
🚀 The 60 Accepted Papers and (tentative) Program for the 3rd Table Representation Learning workshop @NeurIPS '24 are out at: table-representation-learning.github.io!
Also, reply or DM @madelonhulsebos.bsky.social if you/others should be added to the TRL researcher starterpack: go.bsky.app/4SNSMRj!
Also, reply or DM @madelonhulsebos.bsky.social if you/others should be added to the TRL researcher starterpack: go.bsky.app/4SNSMRj!
November 18, 2024 at 7:56 PM
🚀 The 60 Accepted Papers and (tentative) Program for the 3rd Table Representation Learning workshop @NeurIPS '24 are out at: table-representation-learning.github.io!
Also, reply or DM @madelonhulsebos.bsky.social if you/others should be added to the TRL researcher starterpack: go.bsky.app/4SNSMRj!
Also, reply or DM @madelonhulsebos.bsky.social if you/others should be added to the TRL researcher starterpack: go.bsky.app/4SNSMRj!
Reposted by Sascha Marton
Can deep learning finally compete with boosted trees on tabular data? 🌲
In our NeurIPS 2024 paper, we introduce RealMLP, a NN with improvements in all areas and meta-learned default parameters.
Some insights about RealMLP and other models on large benchmarks (>200 datasets): 🧵
In our NeurIPS 2024 paper, we introduce RealMLP, a NN with improvements in all areas and meta-learned default parameters.
Some insights about RealMLP and other models on large benchmarks (>200 datasets): 🧵
November 18, 2024 at 2:15 PM
Can deep learning finally compete with boosted trees on tabular data? 🌲
In our NeurIPS 2024 paper, we introduce RealMLP, a NN with improvements in all areas and meta-learned default parameters.
Some insights about RealMLP and other models on large benchmarks (>200 datasets): 🧵
In our NeurIPS 2024 paper, we introduce RealMLP, a NN with improvements in all areas and meta-learned default parameters.
Some insights about RealMLP and other models on large benchmarks (>200 datasets): 🧵