2 papers
stat.ML2024
Beyond likelihood ratio bias: Nested multi-time-scale stochastic approximation for likelihood-free parameter estimation
Zehao Li, Zhouchen Lin, Yijie Peng
We study parameter inference in simulation-based stochastic models where the analytical form of the likelihood is unknown. The main difficulty is that score evaluation as a ratio o…
cs.LG2023
CORE: Common Random Reconstruction for Distributed Optimization with Provable Low Communication Complexity
Pengyun Yue, Hanzhen Zhao, Cong Fang +4
With distributed machine learning being a prominent technique for large-scale machine learning tasks, communication complexity has become a major bottleneck for speeding up trainin…