Manuscripts

An Information-theoretic Analysis of Edge-reinforced Random Walks

Qinghua (Devon) Ding, Venkat Anantharam. Manuscript on ArXiv.

True Self-Avoiding Walk for Accelerating Markov-Chain Monte Carlo Integration

Qinghua (Devon) Ding, Venkat Anantharam. Manuscript in preparation.

The Double Dixie Cup Problem on General Graphs

with Venkat Anantharam. Manuscript in preparation.

Publications

On Statistical Estimation of Edge-Reinforced Random Walks

Qinghua (Devon) Ding, Venkat Anantharam. ISIT '25, Jack Keil Wolf Best Student Paper Award.

Efficient Estimation of Graph Statistic via Generalized Intersection Local Times

with Venkat Anantharam. Presented at INFORMS Annual Meeting '25.

Usefulness-Driven Learning of Formal Mathematics

Timothe Kaserial, Thomas Lu, Qinghua Ding, Jingxuan He, and Dawn Song. Workshop paper.

Concavity of output relative entropy for channels with binary inputs

with Ken Lau, Chandra Nair, and Dustin Wang. ISIT '21.

Learning and Testing Markov Chains via the k-cover Time

with Siuon Chan and Ray Li. ALT '21.

Empirical Properties of Good Channel Codes

with Sidharth Jaggi, Shashank Vatedka, and Yihan Zhang. ISIT '20.

Tight Convergence Rate of Gradient Descent for Eigenvalue Computation

Qinghua Ding, Kaiwen Zhou, James Cheng. IJCAI '20.

Amortized Nesterov's Momentum: A Robust Momentum and Its Application to Deep Learning

Kaiwen Zhou, Yanghua Jin, Qinghua Ding, James Cheng. UAI '20.

Direct Acceleration of SAGA using Sampled Negative Momentum

Kaiwen Zhou, Qinghua Ding, Fanhua Shang, James Cheng, Danli Li, Zhi-Quan Luo. AISTATS '19.