3 papers
stat.CO2026
Weak Poincaré inequalities for Deterministic-scan Metropolis-within-Gibbs samplers
Mengxi Gao, Gareth O. Roberts, Andi Q. Wang
Using the framework of weak Poincaré inequalities, we analyze the convergence properties of deterministic-scan Metropolis-within-Gibbs samplers, an important class of Markov chain…
math.NT2024
On the representation of large even integers as the sum of eight primes from positive density sets
Meng Gao
We prove that if A is a subset of the primes, and the lower density of A in the primes is larger than 1/2, then every sufficiently large even integer can be written as the sum of e…
cs.LG2024
Cooperative Backdoor Attack in Decentralized Reinforcement Learning with Theoretical Guarantee
Mengtong Gao, Yifei Zou, Zuyuan Zhang +2
The safety of decentralized reinforcement learning (RL) is a challenging problem since malicious agents can share their poisoned policies with benign agents. The paper investigates…