Grigoris Velegkas

According to our database, Grigoris Velegkas authored at least 30 papers between 2019 and 2025.

Collaborative distances:

• Dijkstra number of three.
• Erdős number of three.

2025

On Union-Closedness of Language Generation.

Steve Hanneke, Amin Karbasi, Anay Mehrotra, Grigoris Velegkas

CoRR, June, 2025

(Im)possibility of Automated Hallucination Detection in Large Language Models.

Amin Karbasi, Omar Montasser, John Sous, Grigoris Velegkas

CoRR, April, 2025

On Agnostic PAC Learning in the Small Error Regime.

Julian Asilis, Mikael Møller Høgsgaard, Grigoris Velegkas

CoRR, February, 2025

On the Limits of Language Generation: Trade-Offs between Hallucination and Mode-Collapse.

Alkis Kalavasis, Anay Mehrotra, Grigoris Velegkas

Proceedings of the 57th Annual ACM Symposium on Theory of Computing, 2025

Understanding Aggregations of Proper Learners in Multiclass Classification.

Julian Asilis, Mikael Møller Høgsgaard, Grigoris Velegkas

Proceedings of the International Conference on Algorithmic Learning Theory, 2025

2024

Characterizations of Language Generation With Breadth.

Alkis Kalavasis, Anay Mehrotra, Grigoris Velegkas

CoRR, 2024

Procurement Auctions via Approximately Optimal Submodular Optimization.

Yuan Deng, Amin Karbasi, Vahab Mirrokni, Renato Paes Leme, Grigoris Velegkas, Song Zuo

CoRR, 2024

Injecting Undetectable Backdoors in Deep Learning and Language Models.

Alkis Kalavasis, Amin Karbasi, Argyris Oikonomou, Katerina Sotiraki, Grigoris Velegkas, Manolis Zampetakis

CoRR, 2024

Pointwise Lipschitz Continuous Graph Algorithms via Proximal Gradient Analysis.

Quanquan C. Liu, Grigoris Velegkas, Yuichi Yoshida, Felix Zhou

CoRR, 2024

User Response in Ad Auctions: An MDP Formulation of Long-term Revenue Optimization.

Yang Cai, Zhe Feng, Christopher Liaw, Aranyak Mehta, Grigoris Velegkas

Proceedings of the ACM on Web Conference 2024, 2024

On the Computational Landscape of Replicable Learning.

Alkis Kalavasis, Amin Karbasi, Grigoris Velegkas, Felix Zhou

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Injecting Undetectable Backdoors in Obfuscated Neural Networks and Language Models.

Alkis Kalavasis, Amin Karbasi, Argyris Oikonomou, Katerina Sotiraki, Grigoris Velegkas, Manolis Zampetakis

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Universal Rates for Active Learning.

Steve Hanneke, Amin Karbasi, Shay Moran, Grigoris Velegkas

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Randomized Truthful Auctions with Learning Agents.

Gagan Aggarwal, Anupam Gupta, Andrés Perlroth, Grigoris Velegkas

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Replicable Learning of Large-Margin Halfspaces.

Alkis Kalavasis, Amin Karbasi, Kasper Green Larsen, Grigoris Velegkas, Felix Zhou

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Universal Rates for Regression: Separations between Cut-Off and Absolute Loss.

Idan Attias, Steve Hanneke, Alkis Kalavasis, Amin Karbasi, Grigoris Velegkas

Proceedings of the Thirty Seventh Annual Conference on Learning Theory, June 30, 2024

2023

Replicability in Reinforcement Learning.

Amin Karbasi, Grigoris Velegkas, Lin Yang, Felix Zhou

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Replicable Clustering.

Hossein Esfandiari, Amin Karbasi, Vahab Mirrokni, Grigoris Velegkas, Felix Zhou

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Optimal Learners for Realizable Regression: PAC Learning and Online Learning.

Idan Attias, Steve Hanneke, Alkis Kalavasis, Amin Karbasi, Grigoris Velegkas

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Statistical Indistinguishability of Learning Algorithms.

Alkis Kalavasis, Amin Karbasi, Shay Moran, Grigoris Velegkas

Proceedings of the International Conference on Machine Learning, 2023

Replicable Bandits.

Hossein Esfandiari, Alkis Kalavasis, Amin Karbasi, Andreas Krause, Vahab Mirrokni, Grigoris Velegkas

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

Reproducible Bandits.

Hossein Esfandiari, Alkis Kalavasis, Amin Karbasi, Andreas Krause, Vahab Mirrokni, Grigoris Velegkas

CoRR, 2022

The Best of Both Worlds: Reinforcement Learning with Logarithmic Regret and Policy Switches.

Grigoris Velegkas, Zhuoran Yang, Amin Karbasi

CoRR, 2022

Is Selling Complete Information (Approximately) Optimal?

Dirk Bergemann, Yang Cai, Grigoris Velegkas, Mingfei Zhao

Proceedings of the EC '22: The 23rd ACM Conference on Economics and Computation, Boulder, CO, USA, July 11, 2022

Reinforcement Learning with Logarithmic Regret and Policy Switches.

Grigoris Velegkas, Zhuoran Yang, Amin Karbasi

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Multiclass Learnability Beyond the PAC Framework: Universal Rates and Partial Concept Classes.

Alkis Kalavasis, Grigoris Velegkas, Amin Karbasi

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Universal Rates for Interactive Learning.

Steve Hanneke, Amin Karbasi, Shay Moran, Grigoris Velegkas

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

2021

An Efficient <i>∊</i>-BIC to BIC Transformation and Its Application to Black-Box Reduction in Revenue Maximization.

Yang Cai, Argyris Oikonomou, Grigoris Velegkas, Mingfei Zhao

Proceedings of the 2021 ACM-SIAM Symposium on Discrete Algorithms, 2021

How to Sell Information Optimally: An Algorithmic Study.

Yang Cai, Grigoris Velegkas

Proceedings of the 12th Innovations in Theoretical Computer Science Conference, 2021

2019

An Efficient ε-BIC to BIC Transformation and Its Application to Black-Box Reduction in Revenue Maximization.

Yang Cai, Argyris Oikonomou, Grigoris Velegkas, Mingfei Zhao

CoRR, 2019