5 papers
High-Order Talagrand and Eldan--Gross Inequalities via Besov-Type Variance Functionals
Guangyue Han, Peijie Li
By introducing high-order Besov-type variance functionals that generalize the canonical variance, we develop a unified framework for proving high-order Talagrand-type inequalities…
Information-Theoretic Bounds for Sparse Covariance Estimation in the Vertical-Split Distributed Model
Jing Yee Tan, Guangyue Han
We study the minimax estimation error for distributed covariance matrix estimation in the vertical-split (feature-split) setting, where two agents each observe different coordinate…
Universal Feature Selection with Noisy Observations and Weak Symmetry Conditions
Dier Tang, Guangyue Han
This paper relaxes the restrictive symmetry conditions adopted in [4], [5] and extends their universal feature selection framework to accommodate noisy observations as well as attr…
Second-Order Schalkwijk-Kailath Coding for Autoregressive Gaussian Channels
Jun Su, Guangyue Han, Shlomo Shamai
We study communication with noiseless feedback over Gaussian channels with stationary autoregressive noise of arbitrary finite order. We introduce a class of Gaussian feedback codi…
Strengthening Han's Fourier Entropy-Influence Inequality via an Information-Theoretic Proof
Peijie Li, Guangyue Han
We strengthen Han's Fourier entropy-influence inequality originally proved for -va…