Papers
Communities
Events
Blog
Pricing
Search
Open menu
Home
Papers
2311.00235
Cited By
Implicit biases in multitask and continual learning from a backward error analysis perspective
1 November 2023
Benoit Dherin
Re-assign community
ArXiv
PDF
HTML
Papers citing
"Implicit biases in multitask and continual learning from a backward error analysis perspective"
5 / 5 papers shown
Title
Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning
Alexey Rukhovich
Alexander Podolskiy
Irina Piontkovskaya
45
0
0
28 Jan 2025
Deep Fusion: Efficient Network Training via Pre-trained Initializations
Hanna Mazzawi
X. Gonzalvo
Michael Wunder
Sammy Jerome
Benoit Dherin
AI4CE
33
3
0
20 Jun 2023
Why neural networks find simple solutions: the many regularizers of geometric complexity
Benoit Dherin
Michael Munn
M. Rosca
David Barrett
53
30
0
27 Sep 2022
Continual evaluation for lifelong learning: Identifying the stability gap
Matthias De Lange
Gido M. van de Ven
Tinne Tuytelaars
CLL
91
41
0
26 May 2022
Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization
Stanislaw Jastrzebski
Devansh Arpit
Oliver Åstrand
Giancarlo Kerg
Huan Wang
Caiming Xiong
R. Socher
Kyunghyun Cho
Krzysztof J. Geras
AI4CE
184
65
0
28 Dec 2020
1