31 citations · 65 across the 57 of their papers we have counts for
9 papers · 1 filter
Privacy Preserving Gossip Learning
Erkan Bayram, Mohamed-Ali Belabbas, Tamer Başar
We propose a decentralized privacy-preserving learning algorithm in which each agent holds a single private sample and a shared model. Samples are learned sequentially, and each up…
Adaptive Agent Design
Raj Kiriti Velicheti, Subhonmesh Bose, Tamer Başar
We consider an agent acting against a general non-Markovian environment. The agent maintains its agent states, but is free to choose a transition kernel across those states and opt…
Independent Reinforcement Learning in Discounted Markov Games
Asrin Efe Yorulmaz, Ugur Aydin, Tamer Basar
In this work, we study radically uncoupled learning in discounted general-sum Markov games. Assuming `` for ", we show that, for every fixed discount f…
Shared Infrastructure Investment and Pricing: Stackelberg Equilibria in Risk-Aware Take-or-Pay Contracts
Amal Sakr, Andrea Araldo, Tamer Başar +1
We study a shared infrastructure deployed by an Infrastructure Provider (InP) and used by multiple firms generating revenues through resource usage. We focus on a challenging setti…
Network-Induced Strategic Communication in Opinion Dynamics
Hassan Munif, Anthony Couthures, Vineeth S. Varma +2
Classical opinion dynamics typically assume a fixed mapping from private opinions to public signals, such as linear exchange, saturated signaling, or discrete public actions. In th…
Continuity of VaR and Continuous Differentiability of CVaR under Decision-Dependent Losses
Amal Sakr, Andrea Araldo, Tamer Başar +1
Value-at-risk (VaR) and conditional value-at-risk (CVaR) are widely used in risk-aware optimization and equilibrium models. When the loss depends on a decision variable, the induce…
Cooperative and Noncooperative Paradigms for Game-Theoretic Control of Socio-Technical Systems
Tamer Başar, Tomohisa Hayakawa, Hideaki Ishii +1
This tutorial presents cooperative and noncooperative game-theoretic frameworks for modeling, learning, and control in socio-technical systems, where human behavior, incentives, in…
A Stackelberg Game Framework with Drainability Guardrails for Pricing and Scaling in Multi-Tenant GPU Cloud Platforms
Junji Yan, Asrin Efe Yorulmaz, Hanchen Zhou +1
Modern Graphics Processing Unit (GPU)-backed services must satisfy strict latency service-level objectives (SLOs) while controlling spare-capacity costs. In multi-tenant GPU cloud…
Meta-Learning for Repeated Bayesian Persuasion
Ata Poyraz Turna, Asrin Efe Yorulmaz, Tamer Başar
Classical Bayesian persuasion studies how a sender influences receivers through carefully designed signaling policies within a single strategic interaction. In many real-world envi…