Följ
Alkis Kalavasis
Alkis Kalavasis
Yale University
Verifierad e-postadress på yale.edu - Startsida
Titel
Citeras av
Citeras av
År
Statistical indistinguishability of learning algorithms
A Kalavasis, A Karbasi, S Moran, G Velegkas
International Conference on Machine Learning 40, 2023
282023
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, 2023
252023
Replicable bandits
H Esfandiari, A Kalavasis, A Karbasi, A Krause, V Mirrokni, G Velegkas
arXiv preprint arXiv:2210.01898, 2022
252022
Efficient parameter estimation of truncated boolean product distributions
D Fotakis, A Kalavasis, C Tzamos
Conference on learning theory, 1586-1600, 2020
212020
Efficient algorithms for learning from coarse labels
D Fotakis, A Kalavasis, V Kontonis, C Tzamos
Conference on Learning Theory, 2060-2079, 2021
192021
Differentially private regression with unbounded covariates
J Milionis, A Kalavasis, D Fotakis, S Ioannidis
International Conference on Artificial Intelligence and Statistics, 3242-3273, 2022
152022
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, 2022
142022
Replicable learning of large-margin halfspaces
A Kalavasis, A Karbasi, KG Larsen, G Velegkas, F Zhou
arXiv preprint arXiv:2402.13857, 2024
92024
Label ranking through nonparametric regression
D Fotakis, A Kalavasis, E Psaroudaki
International Conference on Machine Learning, 6622-6659, 2022
92022
Aggregating incomplete and noisy rankings
D Fotakis, A Kalavasis, K Stavropoulos
International conference on artificial intelligence and statistics, 2278-2286, 2021
82021
Optimizing Solution-Samplers for Combinatorial Problems: The Landscape of Policy-Gradient Methods
C Caramanis, D Fotakis, A Kalavasis, V Kontonis, C Tzamos
Advances in Neural Information Processing Systems 36, 2023
62023
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
42024
Transfer learning beyond bounded density ratios
A Kalavasis, I Zadik, M Zampetakis
arXiv preprint arXiv:2403.11963, 2024
42024
On the complexity of computing sparse equilibria and lower bounds for no-regret learning in games
I Anagnostides, A Kalavasis, T Sandholm, M Zampetakis
arXiv preprint arXiv:2311.14869, 2023
42023
Linear label ranking with bounded noise
D Fotakis, A Kalavasis, V Kontonis, C Tzamos
Advances in Neural Information Processing Systems 35, 15642-15656, 2022
42022
Perfect Sampling from Pairwise Comparisons
D Fotakis, A Kalavasis, C Tzamos
Advances in Neural Information Processing Systems 35, 2022
42022
On sampling from Ising models with spectral constraints
A Galanis, A Kalavasis, AV Kandiros
arXiv preprint arXiv:2407.07645, 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
On the computational landscape of replicable learning
A Kalavasis, A Karbasi, G Velegkas, F Zhou
arXiv preprint arXiv:2405.15599, 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
Systemet kan inte utföra åtgärden just nu. Försök igen senare.
Artiklar 1–20