Seguir
Grigoris Velegkas
Grigoris Velegkas
Yale University
E-mail confirmado em yale.edu - Página inicial
Título
Citado por
Citado por
Ano
Statistical indistinguishability of learning algorithms
A Kalavasis, A Karbasi, S Moran, G Velegkas
International Conference on Machine Learning, 15586-15622, 2023
282023
An Efficient ∊-BIC to BIC Transformation and Its Application to Black-Box Reduction in Revenue Maximization
Y Cai, A Oikonomou, G Velegkas, M Zhao
Proceedings of the 2021 acm-siam symposium on discrete algorithms (soda …, 2021
28*2021
Optimal learners for realizable regression: Pac learning and online learning
I Attias, S Hanneke, A Kalavasis, A Karbasi, G Velegkas
Advances in Neural Information Processing Systems 36, 44707-44739, 2023
252023
Replicable bandits
H Esfandiari, A Kalavasis, A Karbasi, A Krause, V Mirrokni, G Velegkas
arXiv preprint arXiv:2210.01898, 2022
252022
Replicable clustering
H Esfandiari, A Karbasi, V Mirrokni, G Velegkas, F Zhou
Advances in Neural Information Processing Systems 36, 39277-39320, 2023
212023
Multiclass learnability beyond the pac framework: Universal rates and partial concept classes
A Kalavasis, G Velegkas, A Karbasi
Advances in Neural Information Processing Systems 35, 20809-20822, 2022
142022
Replicability in reinforcement learning
A Karbasi, G Velegkas, L Yang, F Zhou
Advances in Neural Information Processing Systems 36, 74702-74735, 2023
132023
Is Selling Complete Information (Approximately) Optimal?
D Bergemann, Y Cai, G Velegkas, M Zhao
Proceedings of the 23rd ACM Conference on Economics and Computation, 608-663, 2022
132022
How to sell information optimally: An algorithmic study
Y Cai, G Velegkas
arXiv preprint arXiv:2011.14570, 2020
122020
Replicable learning of large-margin halfspaces
A Kalavasis, A Karbasi, KG Larsen, G Velegkas, F Zhou
arXiv preprint arXiv:2402.13857, 2024
92024
Universal rates for interactive learning
S Hanneke, A Karbasi, S Moran, G Velegkas
Advances in Neural Information Processing Systems 35, 28657-28669, 2022
62022
Reinforcement learning with logarithmic regret and policy switches
G Velegkas, Z Yang, A Karbasi
Advances in Neural Information Processing Systems 35, 36040-36053, 2022
4*2022
On the limits of language generation: Trade-offs between hallucination and mode collapse
A Kalavasis, A Mehrotra, G Velegkas
arXiv preprint arXiv:2411.09642, 2024
32024
Universal Rates for Regression: Separations between Cut-Off and Absolute Loss
I Attias, S Hanneke, A Kalavasis, A Karbasi, G Velegkas
The Thirty Seventh Annual Conference on Learning Theory, 359-405, 2024
32024
Understanding Aggregations of Proper Learners in Multiclass Classification
J Asilis, MM Høgsgaard, G Velegkas
arXiv preprint arXiv:2410.22749, 2024
22024
Injecting Undetectable Backdoors in Obfuscated Neural Networks and Language Models
A Kalavasis, A Karbasi, A Oikonomou, K Sotiraki, G Velegkas, ...
The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024
2*2024
On the computational landscape of replicable learning
A Kalavasis, A Karbasi, G Velegkas, F Zhou
arXiv preprint arXiv:2405.15599, 2024
22024
Characterizations of language generation with breadth
A Kalavasis, A Mehrotra, G Velegkas
arXiv preprint arXiv:2412.18530, 2024
12024
Randomized truthful auctions with learning agents
G Aggarwal, A Gupta, A Perlroth, G Velegkas
Advances in Neural Information Processing Systems 37, 38007-38034, 2024
12024
On Agnostic PAC Learning in the Small Error Regime
J Asilis, MM Høgsgaard, G Velegkas
arXiv preprint arXiv:2502.09496, 2025
2025
O sistema não pode executar a operação agora. Tente novamente mais tarde.
Artigos 1–20