7 citations · 16 across the 9 of their papers we have counts for
10 papers
Throughput-Optimal Scheduling via Rate Learning
Panagiotis Promponas, Víctor Valls, Konstantinos Nikolakakis +2
We study the problem of designing scheduling policies for communication networks. This problem is often addressed with max-weight-type approaches since they are throughput-optimal.…
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
The NOSTR is a communication protocol for the social web, based on the w3c websockets standard. Although it is still in its infancy, it is well known as a social media protocol, wi…
Federated Learning Under Restricted User Availability
Periklis Theodoropoulos, Konstantinos E. Nikolakakis, Dionysis Kalogerias
Federated Learning (FL) is a decentralized machine learning framework that enables collaborative model training while respecting data privacy. In various applications, non-uniform…
Repeated Random Sampling for Minimizing the Time-to-Accuracy of Learning
Patrik Okanovic, Roger Waleffe, Vasilis Mageirakos +5
Methods for carefully selecting or generating a small set of training data to learn from, i.e., data pruning, coreset selection, and data distillation, have been shown to be effect…
Select without Fear: Almost All Mini-Batch Schedules Generalize Optimally
Konstantinos E. Nikolakakis, Amin Karbasi, Dionysis Kalogerias
We establish matching upper and lower generalization error bounds for mini-batch Gradient Descent (GD) training with either deterministic or stochastic, data-independent, but other…
Beyond Lipschitz: Sharp Generalization and Excess Risk Bounds for Full-Batch GD
Konstantinos E. Nikolakakis, Farzin Haddadpour, Amin Karbasi +1
We provide sharp path-dependent generalization and excess risk guarantees for the full-batch Gradient Descent (GD) algorithm on smooth losses (possibly non-Lipschitz, possibly nonc…
Black-Box Generalization: Stability of Zeroth-Order Learning
Konstantinos E. Nikolakakis, Farzin Haddadpour, Dionysios S. Kalogerias +1
We provide the first generalization error analysis for black-box learning through derivative-free optimization. Under the assumption of a Lipschitz and smooth unknown loss, we cons…
Quantile Multi-Armed Bandits: Optimal Best-Arm Identification and a Differentially Private Scheme
Kontantinos E. Nikolakakis, Dionysios S. Kalogerias, Or Sheffet +1
We study the best-arm identification problem in multi-armed bandits with stochastic, potentially private rewards, when the goal is to identify the arm with the highest quantile at…
Optimal Rates for Learning Hidden Tree Structures
Konstantinos E. Nikolakakis, Dionysios S. Kalogerias, Anand D. Sarwate
We provide high probability finite sample complexity guarantees for hidden non-parametric structure learning of tree-shaped graphical models, whose hidden and observable nodes are…
Predictive Learning on Hidden Tree-Structured Ising Models
Konstantinos E. Nikolakakis, Dionysios S. Kalogerias, Anand D. Sarwate
We provide high-probability sample complexity guarantees for exact structure recovery and accurate predictive learning using noise-corrupted samples from an acyclic (tree-shaped) g…