Resources

Recordings

More are coming soon!

Technical Reports

Below you can find the technical reports of participants who summarized their approaches in writing reports:

  1. "Representation Based Complexity Measures for Predicting Generalization in Deep Learning". Parth Netakar and Manik Sharma. Team "Interpex".

  2. "Robustness to Augmentations as a Generalization Metric". Sumukh Aithal K, Dhruva Kashyap, Natarajan Subramanyam. Team "Always Generalize".

  3. "Ranking Deep Learning Generalization using Label Variation in Latent Geometry Graphs". Carlos Lassance et al. Team "BrAIn"

  4. "Using noise resilience for ranking generalization of deep neural networks". Depen Morwani, Rahul Vashisht, Harish Guruprasad Ramaswamy.

  5. "Predicting Generalization in Deep Learning via Metric Learning – PGDL Shared task". Sebastian Mežnar, Blaž Škrlj.

  6. "Predicting Deep Learning Model Generalization Using Asymptotic Stability". Lin Zhang, Shaohua Li, Ling Feng. Team "FZL".

  7. "Predicting generalization using measures of intraclass clustering". Simon Carbonnelle, Christophe De Vleeschouwer.

  8. "Predicting Generalization in Deep Learning via Local Measures of Distortion". Abhejit Rajagopal, Vamshi C. Madala, Shivkumar Chandrasekaran, Peder E. Z. Larson. Team "inv3rse".

  9. "Fractal Dimension Generalization Measure". Valeri Alexiev. Team "Strange Attractor".

Dataset

The PGDL datasets for all phases of the competition can be found here.

Other Resources