firstbacksecondback
31 Results
|
Poster
|
Tue 1:00 |
Computational Separation Between Convolutional and Fully-Connected Networks Eran Malach · Shai Shalev-Shwartz |
|
|
Poster
|
Mon 17:00 |
Optimal Regularization can Mitigate Double Descent Preetum Nakkiran · Prayaag Venkat · Sham M Kakade · Tengyu Ma |
|
|
Poster
|
Wed 9:00 |
Entropic gradient descent algorithms and wide flat minima Fabrizio Pittorino · Carlo Lucibello · Christoph Feinauer · Gabriele Perugini · Carlo Baldassi · Elizaveta Demyanenko · Riccardo Zecchina |
|
|
Spotlight
|
Mon 12:15 |
On the Theory of Implicit Deep Learning: Global Convergence with Implicit Layers Kenji Kawaguchi |
|
|
Poster
|
Wed 9:00 |
Early Stopping in Deep Networks: Double Descent and How to Eliminate it Reinhard Heckel · Fatih Furkan Yilmaz |
|
|
Poster
|
Tue 9:00 |
Towards Resolving the Implicit Bias of Gradient Descent for Matrix Factorization: Greedy Low-Rank Learning Zhiyuan Li · Yuping Luo · Kaifeng Lyu |
|
|
Poster
|
Mon 1:00 |
On the Universality of the Double Descent Peak in Ridgeless Regression David Holzmüller |