1 citations · 1 across the 4 of their papers we have counts for
5 papers
Beyond Length: Quantifying Long-Range Information for Long-Context LLM Pretraining Data
Haoran Deng, Yingyu Lin, Zhenghao Lin +4
Long-context language models unlock advanced capabilities in reasoning, code generation, and document summarization by leveraging dependencies across extended spans of text. Howeve…
Purifying Approximate Differential Privacy with Randomized Post-processing
Yingyu Lin, Erchi Wang, Yi-An Ma +1
We propose a framework to convert -approximate Differential Privacy (DP) mechanisms into -pure DP mechanisms under certain conditions, a proces…
A Skewness-Based Criterion for Addressing Heteroscedastic Noise in Causal Discovery
Yingyu Lin, Yuxing Huang, Wenqin Liu +6
Real-world data often violates the equal-variance assumption (homoscedasticity), making it essential to account for heteroscedastic noise in causal discovery. In this work, we expl…
Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximation
Nikki Lijing Kuang, Ming Yin, Mengdi Wang +2
Recent studies in reinforcement learning (RL) have made significant progress by leveraging function approximation to alleviate the sample complexity hurdle for better performance.…
Tractable MCMC for Private Learning with Pure and Gaussian Differential Privacy
Yingyu Lin, Yi-An Ma, Yu-Xiang Wang +2
Posterior sampling, i.e., exponential mechanism to sample from the posterior distribution, provides -pure differential privacy (DP) guarantees and does not suffer from…