Scholar
Yingyu Lin
Google Scholar ID: lzISLB0AAAAJ
UC San Diego
Citations & Impact
Citations
10
H-index
2
i10-index
0
Publications
5
Co-authors
7
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Beyond Length: Quantifying Long-Range Information for Long-Context LLM Pretraining Data (Preprint)
- On the Complexity Theory of Masked Discrete Diffusion: From poly(1/ε) to Nearly ε-Free (Preprint)
- Almost Linear Convergence under Minimal Score Assumptions: Quantized Transition Diffusion (Preprint)
- Purifying Approximate Differential Privacy with Randomized Post-processing (NeurIPS 2025, Spotlight; TPDP Workshop 2025, Contributed Talk)
- A Skewness-Based Criterion for Addressing Heteroscedastic Noise in Causal Discovery (ICLR 2025)
- Tractable MCMC for Private Learning with Pure and Gaussian Differential Privacy (ICLR 2024)
Research Experience
- Works closely with Yu-Xiang Wang and Biwei Huang.
Education
- Ph.D. student at UC San Diego, advised by Yi-An Ma; B.S. in Mathematics from Tsinghua University.
Background
- Research interests include statistical sampling, Markov chain Monte Carlo (MCMC), differential privacy, diffusion models, and causality.
Miscellany
- Email: yil208@ucsd.edu
