no code implementations • 27 Feb 2023 • Siddharth Chandak, Ilai Bistritz, Nicholas Bambos
We prove that UECB achieves a regret of $\mathcal{O}(\log(T)+\tau_c\log(\tau_c)+\tau_c\log\log(T))$ for this equilibrium bandit problem where $\tau_c$ is the worst case approximate convergence time to equilibrium.
no code implementations • 8 Mar 2021 • Ilai Bistritz, Zhengyuan Zhou, Xi Chen, Nicholas Bambos, Jose Blanchet
Using these bounds, we show that FKM and EXP3 have no weighted-regret even for $d_{t}=O\left(t\log t\right)$.
no code implementations • NeurIPS 2020 • Ilai Bistritz, Nicholas Bambos
At each turn, each player chooses an action and receives a reward that is an unknown function of all the players' actions.
no code implementations • NeurIPS 2020 • Ilai Bistritz, Ariana Mann, Nicholas Bambos
We prove that our algorithm converges with probability 1 to a stationary point where all devices in the communication network distill the entire network's knowledge on the reference data, regardless of their local connections.
no code implementations • NeurIPS 2019 • Ilai Bistritz, Zhengyuan Zhou, Xi Chen, Nicholas Bambos, Jose Blanchet
An adversary chooses the cost of each arm in a bounded interval, and a sequence of feedback delays \left\{ d_{t}\right\} that are unknown to the player.
no code implementations • 3 May 2019 • Ilai Bistritz, Nasimeh Heydaribeni, Achilleas Anastasopoulos
We provide a characterization of perfect Bayesian equilibria (PBE) with forward-looking strategies through a fixed-point equation of dimensionality that grows only quadratically with the number of players.
no code implementations • 17 Feb 2019 • S. M. Zafaruddin, Ilai Bistritz, Amir Leshem, Dusit Niyato
When the CSI is time varying and unknown to the users, the users face the challenge of both learning the channel statistics online and converge to a good channel allocation.
no code implementations • NeurIPS 2018 • Ilai Bistritz, Amir Leshem
Each player has different expected rewards for the arms, and the instantaneous rewards are independent and identically distributed.
