Volgen
Angeliki Giannou
Angeliki Giannou
Geverifieerd e-mailadres voor wisc.edu
Titel
Geciteerd door
Geciteerd door
Jaar
Looped transformers as programmable computers
A Giannou, S Rajput, J Sohn, K Lee, JD Lee, D Papailiopoulos
International Conference on Machine Learning, 11398-11442, 2023
462023
Survival of the strictest: Stable and unstable equilibria under regularized learning with partial information
A Giannou, EV Vlatakis-Gkaragkounis, P Mertikopoulos
Conference on Learning Theory, 2147-2148, 2021
282021
On the rate of convergence of regularized learning in games: From bandits and uncertainty to optimism and beyond
A Giannou, EV Vlatakis-Gkaragkounis, P Mertikopoulos
Advances in Neural Information Processing Systems 34, 22655-22666, 2021
192021
Dissecting chain-of-thought: A study on compositional in-context learning of mlps
Y Li, K Sreenivasan, A Giannou, D Papailiopoulos, S Oymak
arXiv preprint arXiv:2305.18869, 2023
102023
On the convergence of policy gradient methods to Nash equilibria in general stochastic games
A Giannou, K Lotidis, P Mertikopoulos, EV Vlatakis-Gkaragkounis
Advances in Neural Information Processing Systems 35, 7128-7141, 2022
92022
The expressive power of tuning only the norm layers
A Giannou, S Rajput, D Papailiopoulos
arXiv e-prints, arXiv: 2302.07937, 2023
6*2023
Dissecting chain-of-thought: Compositionality through in-context filtering and learning
Y Li, K Sreenivasan, A Giannou, D Papailiopoulos, S Oymak
Advances in Neural Information Processing Systems 36, 2024
32024
Stochastic methods in variational inequalities: Ergodicity, bias and refinements
EV Vlatakis-Gkaragkounis, A Giannou, Y Chen, Q Xie
arXiv preprint arXiv:2306.16502, 2023
22023
How Well Can Transformers Emulate In-context Newton's Method?
A Giannou, L Yang, T Wang, D Papailiopoulos, JD Lee
arXiv preprint arXiv:2403.03183, 2024
2024
Het systeem kan de bewerking nu niet uitvoeren. Probeer het later opnieuw.
Artikelen 1–9