Instance-Specific Sharp Convergence Rate of the Add-λ Estimator via Feature Space Decomposition
Zong Shang
Abstract
Using the Feature Space Decomposition framework, we establish non-asymptotic matching upper and lower bounds for the expected Kullback-Leibler estimation error of the Add-λ estimator of a discrete probability distribution, for any signal, any dimension, any sample size, and any λ>0.
Create a lesson
Related papers
Optimal Communication for Distributed Sparse Histogram Aggregation
Fangwei Ye, Yijun Fan
Hardware-Efficient Reinforcement-Learned Scheduling for Quantum LDPC Decoders
Mohsen Moradi, Vahid Nourozi, Wei Tang et al.
Making Every Edit Count: Efficient Binary Edit Correction at the Gilbert-Varshamov Bound
Ryan Gabrys, Shubhransh Singhvi, Eitan Yaakobi
Timely Ground-Station Status Delivery via UAV-Assisted Data Collection and Hierarchical RL
Xiangjian Gao, Mohammad Moltafet, Hamid R. Sadjadpour
Uniform Sampling of Linear Codes with Prescribed Hull Dimension
Keita Ishizuka
Quantum Private Information Retrieval on Forests
Mohamed Nomeir, Sennur Ulukus