7 citations · 12 across the 22 of their papers we have counts for
24 papers
FedeRage: Provably Convergent Agnostic Federated Learning under General Client Drift
Herlock Rahimi, Dionysis Kalogerias
Federated learning (FL) enables collaborative model training without sharing raw data, but its performance degrades under non-IID data and stochastic client participation. Remedies…
Constrained Learning with Universally Learnable Concept Classes
Herlock SeyedAbolfazl Rahimi, Spyridon Pougkakiotis, Dionysis Kalogerias
We study constrained statistical learning over infinite-dimensional hypothesis classes in the fully nonconvex setting, and establish universal PACC learnability of the solutions of…
Self-Improving In-Context Learning
Baturay Saglam, Dionysis Kalogerias
We propose to improve in-context learning (ICL) by optimizing the continuous embeddings of a fixed few-shot prompt at test time. The key observation is that the log-probabilities a…
Test-Time Safety Alignment
Baturay Saglam, Dionysis Kalogerias
Recent work has shown that a model's input word embeddings can serve as effective control variables for steering its behavior toward outputs that satisfy desired properties. Howeve…
Risk-Aware LQR with Temporally Coupled States
Chuanning Wei, Kin Fung Li, Dionysis Kalogerias +1
We formulate and solve a discrete-time linear-quadratic regulation (LQR) problem in a finite horizon thatpenalizes temporal variability and stochastic variability of the state traj…
Test-Time Detoxification without Training or Learning Anything
Baturay Saglam, Dionysis Kalogerias
Large language models can produce toxic or inappropriate text even for benign inputs, creating risks when deployed at scale. Detoxification is therefore important for safety and us…
Risk-Averse Constrained Reinforcement Learning with Optimized Certainty Equivalents
Jane H. Lee, Baturay Saglam, Spyridon Pougkakiotis +2
Constrained optimization provides a common framework for dealing with conflicting objectives in reinforcement learning (RL). In most of these settings, the objectives (and constrai…
Ultra-Reliable Risk-Aggregated Sum Rate Maximization via Model-Aided Deep Learning
Hassaan Hashmi, Spyridon Pougkakiotis, Dionysis Kalogerias
We consider the problem of maximizing weighted sum rate in a multiple-input single-output (MISO) downlink wireless network with emphasis on user rate reliability. We introduce a no…
Data-Driven Two-Stage IRS-Aided Sumrate Maximization with Inexact Precoding
Hassaan Hashmi, Spyridon Pougkakiotis, Dionysis Kalogerias
We propose iZoSGA, a data-driven learning algorithm for joint passive long-term intelligent reflective surface (IRS)-aided beamforming and active short-term precoding in wireless n…
FedAVOT: Exact Distribution Alignment in Federated Learning via Masked Optimal Transport
Herlock, Rahimi, Dionysis Kalogerias
Federated Learning (FL) allows distributed model training without sharing raw data, but suffers when client participation is partial. In practice, the distribution of available use…
Inexact Zeroth-Order Nonsmooth and Nonconvex Stochastic Composite Optimization and Applications
Spyridon Pougkakiotis, Dionysis Kalogerias
In this paper we present an inexact zeroth-order method suitable for the solution nonsmooth and nonconvex stochastic composite optimization problems, in which the objective is spli…
Convergence of Agnostic Federated Averaging
Herlock, Rahimi, Dionysis Kalogerias
Federated learning (FL) enables decentralized model training without centralizing raw data. However, practical FL deployments often face a key realistic challenge: Clients particip…
Learning Task Representations from In-Context Learning
Baturay Saglam, Xinyang Hu, Zhuoran Yang +2
Large language models (LLMs) have demonstrated remarkable proficiency in in-context learning (ICL), where models adapt to new tasks through example-based prompts without requiring…
Distributionally Robust Power Policies for Wireless Systems under Power Fluctuation Risk
Gokberk Yaylali, Dionysios S. Kalogerias
Modern wireless communication systems necessitate the development of cost-effective resource allocation strategies, while ensuring maximal system performance. While commonly realiz…
Data-Driven Learning of Two-Stage Beamformers in Passive IRS-Assisted Systems with Inexact Oracles
Spyridon Pougkakiotis, Hassaan Hashmi, Dionysis Kalogerias
We develop an efficient data-driven and model-free unsupervised learning algorithm for achieving fully passive intelligent reflective surface (IRS)-assisted optimal short/long-term…
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.…
Compatible Gradient Approximations for Actor-Critic Algorithms
Baturay Saglam, Dionysis Kalogerias
Deterministic policy gradient algorithms are foundational for actor-critic methods in controlling continuous systems, yet they often encounter inaccuracies due to their dependence…
An efficient active-set method with applications to sparse approximations and risk minimization
Spyridon Pougkakiotis, Jacek Gondzio, Dionysis Kalogerias
In this paper we present an efficient active-set method for the solution of convex quadratic programming problems with general piecewise-linear terms in the objective, with applica…
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…
A Distributionally Robust Estimator that Dominates the Empirical Average
Nikolas Koumpis, Dionysis Kalogerias
We leverage the duality between risk-averse and distributionally robust optimization (DRO) to devise a distributionally robust estimator that strictly outperforms the empirical ave…
Strong Duality Relations in Nonconvex Risk-Constrained Learning
Dionysis Kalogerias, Spyridon Pougkakiotis
We establish strong duality relations for functional two-step compositional risk-constrained learning problems with multiple nonconvex loss functions and/or learning constraints, r…
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…
Robust and Reliable Stochastic Resource Allocation via Tail Waterfilling
Gokberk Yaylali, Dionysios S. Kalogerias
Stochastic allocation of resources in the context of wireless systems ultimately demands reactive decision making for meaningfully optimizing network-wide random utilities, while r…