no code implementations • 22 Feb 2024 • Jason Gaitonde, Elchanan Mossel
Here, the $\mathbf{x}_{\ell}$ are assumed to be $\mathcal{N}(0, I_n)$ and the noise distribution $\mathbf{\eta}_{\ell}\sim \mathcal{D}$ is centered and independent of $\mathbf{x}_{\ell}$.
no code implementations • 15 Nov 2023 • Jason Gaitonde, Elchanan Mossel
We show that a simple existing approach based on node-wise logistic regression provably succeeds at recovering the underlying model in several new settings where these assumptions are violated: (1) Given dynamically generated data from a wide variety of local Markov chains, like block or round-robin dynamics, logistic regression recovers the parameters with optimal sample complexity up to $\log\log n$ factors.
no code implementations • 16 Mar 2020 • Jason Gaitonde, Eva Tardos
In this paper, we study this phenomenon in the context of a game modeling queuing systems: routers compete for servers, where packets that do not get service will be resent at future rounds, resulting in a system where the number of packets at each round depends on the success of the routers in the previous rounds.
no code implementations • 16 Mar 2020 • Jason Gaitonde, Jon Kleinberg, Eva Tardos
We study the connections between network structure, opinion dynamics, and an adversary's power to artificially induce disagreements.
Data Structures and Algorithms Computer Science and Game Theory Social and Information Networks Physics and Society