Chenyu Gan

collaborators

4 papers

cs.LG2026

Square-Root Regret for Adversarial Multiplayer Bandits without Collision Information or Shared Randomness

Chenyu Gan

We study adversarial multiplayer bandits with $K$ arms and $2 \leq m < K$ labeled players, without collision information, shared randomness, or an external communication channel. We de…

math.PR2026

Consensus time for asynchronous $ℓ^{p}$ relaxation: graph dependence

Chenyu Gan

We study the asynchronous $ℓ^{p}$ relaxation introduced by Amir, Nazarov, and Peres: at each step, a uniformly chosen vertex minimizes its incident $ℓ^{p}$ energy. For the profil…

cs.LG2026

Rising Multi-Armed Bandits with Known Horizons

Seockbean Song, Chenyu Gan, Youngsik Yoon +3

Rising Multi-Armed Bandits (RMABs) model sequential decision problems where each arm's expected reward improves with repeated pulls. In such problems, the value of investing in an…

math.PR2025

Convergence rate of $ℓ^{p}$ -relaxation on a graph to a $p$ -harmonic function with given boundary values

Chenyu Gan, Yuval Peres, Junchi Zuo

We analyze the following dynamics on a connected graph $(V, E)$ with $n$ vertices. Let $V = I ⋃ B$ , where the set of interior vertices $I \neq = \emptyset$ is disjoint from the s…

Square-Root Regret for Adversarial Multiplayer Bandits without Collision Information or Shared Randomness

Consensus time for asynchronous ℓp relaxation: graph dependence

Rising Multi-Armed Bandits with Known Horizons

Convergence rate of ℓp-relaxation on a graph to a p-harmonic function with given boundary values

Consensus time for asynchronous $ℓ^{p}$ relaxation: graph dependence

Convergence rate of $ℓ^{p}$ -relaxation on a graph to a $p$ -harmonic function with given boundary values