Notice détaillée
Titre
Pethick, Thomas Michaelsen
Sciper ID
300408
Laboratoires affiliés
LIONS
Publications
Escaping limit cycles: Global convergence for constrained nonconvex-nonconcave minimax problems
Federated Learning under Covariate Shifts with Generalization Guarantees
Finding Actual Descent Directions For Adversarial Training
Revisiting adversarial training for the worst-performing class
Sifting through the Noise: Universal First-Order Methods for Stochastic Variational Inequalities
Solving stochastic weak Minty variational inequalities without increasing batch size
Stable Nonconvex-Nonconcave Training via Linear Interpolation
Federated Learning under Covariate Shifts with Generalization Guarantees
Finding Actual Descent Directions For Adversarial Training
Revisiting adversarial training for the worst-performing class
Sifting through the Noise: Universal First-Order Methods for Stochastic Variational Inequalities
Solving stochastic weak Minty variational inequalities without increasing batch size
Stable Nonconvex-Nonconcave Training via Linear Interpolation
Toutes les ressources
Toutes les ressources
Le document apparaît dans
Authorities > People