Konstantinos E. Nikolakakis

According to our database, Konstantinos E. Nikolakakis authored at least 15 papers between 2018 and 2025.

Collaborative distances:

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

2025

Select without Fear: Almost All Minibatch Schedules Generalize Optimally.

Konstantinos E. Nikolakakis, Amin Karbasi, Dionysis Kalogerias

SIAM J. Math. Data Sci., 2025

2024

FEDSTR: Money-In AI-Out | A Decentralized Marketplace for Federated Learning and LLM Training on the NOSTR Protocol.

Konstantinos E. Nikolakakis, George Chantzialexiou, Dionysis Kalogerias

CoRR, 2024

Repeated Random Sampling for Minimizing the Time-to-Accuracy of Learning.

Patrik Okanovic, Roger Waleffe, Vasilis Mageirakos, Konstantinos E. Nikolakakis, Amin Karbasi, Dionysios S. Kalogerias, Nezihe Merve Gürel, Theodoros Rekatsinas

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Federated Learning under Restricted user Availability.

Periklis Theodoropoulos, Konstantinos E. Nikolakakis, Dionysis Kalogerias

Proceedings of the IEEE International Conference on Acoustics, 2024

Throughput-Optimal Scheduling via Rate Learning.

Panagiotis Promponas, Víctor Valls, Konstantinos E. Nikolakakis, Dionysis Kalogerias, Leandros Tassiulas

Proceedings of the 63rd IEEE Conference on Decision and Control, 2024

2023

Select without Fear: Almost All Mini-Batch Schedules Generalize Optimally.

Konstantinos E. Nikolakakis, Amin Karbasi, Dionysis Kalogerias

CoRR, 2023

Beyond Lipschitz: Sharp Generalization and Excess Risk Bounds for Full-Batch GD.

Konstantinos E. Nikolakakis, Farzin Haddadpour, Amin Karbasi, Dionysios S. Kalogerias

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

Black-Box Generalization.

Konstantinos E. Nikolakakis, Farzin Haddadpour, Dionysios S. Kalogerias, Amin Karbasi

CoRR, 2022

Black-Box Generalization: Stability of Zeroth-Order Learning.

Konstantinos E. Nikolakakis, Farzin Haddadpour, Dionysios S. Kalogerias, Amin Karbasi

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

2021

Quantile Multi-Armed Bandits: Optimal Best-Arm Identification and a Differentially Private Scheme.

Konstantinos E. Nikolakakis, Dionysios S. Kalogerias, Or Sheffet, Anand D. Sarwate

IEEE J. Sel. Areas Inf. Theory, 2021

Predictive Learning on Hidden Tree-Structured Ising Models.

Konstantinos E. Nikolakakis, Dionysios S. Kalogerias, Anand D. Sarwate

J. Mach. Learn. Res., 2021

2020

Best-Arm Identification for Quantile Bandits with Privacy.

Dionysios S. Kalogerias, Konstantinos E. Nikolakakis, Anand D. Sarwate, Or Sheffet

CoRR, 2020

2019

Non-Parametric Structure Learning on Hidden Tree-Shaped Distributions.

Konstantinos E. Nikolakakis, Dionysios S. Kalogerias, Anand D. Sarwate

CoRR, 2019

Learning Tree Structures from Noisy Data.

Konstantinos E. Nikolakakis, Dionysios S. Kalogerias, Anand D. Sarwate

Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

2018

Predictive Learning on Sign-Valued Hidden Markov Trees.

Konstantinos E. Nikolakakis, Dionysios S. Kalogerias, Anand D. Sarwate

CoRR, 2018