Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Privacy Amplification in Differentially Private Zeroth-Order Optimization with Hidden States
Eli Chien, Wei-Ning Chen, Pan Li
Zeroth-order optimization has emerged as a promising approach for fine-tuning large language models under differential privacy (DP) and memory constraints. While privacy amplificat…
cs.LG2025
Privately Learning from Graphs with Applications in Fine-tuning Large Language Models
Haoteng Yin, Rongzhe Wei, Eli Chien +1
Graphs offer unique insights into relationships between entities, complementing data modalities like text and images and enabling AI models to extend their capabilities beyond trad…
cs.LG2025
Convergent Privacy Loss of Noisy-SGD without Convexity and Smoothness
Eli Chien, Pan Li
We study the Differential Privacy (DP) guarantee of hidden-state Noisy-SGD algorithms over a bounded domain. Standard privacy analysis for Noisy-SGD assumes all internal states are…