2 papers
cs.LG2025
Almost Sure Convergence Analysis of Differentially Private Stochastic Gradient Methods
Amartya Mukherjee, Jun Liu
Differentially private stochastic gradient descent (DP-SGD) has become the standard algorithm for training machine learning models with rigorous privacy guarantees. Despite its wid…
cs.RO2024
Signal Temporal Logic Planning with Time-Varying Robustness
Yating Yuan, Thanin Quartz, Jun Liu
This letter aims to generate a continuous-time trajectory consisting of piecewise Bézier curves that satisfy signal temporal logic (STL) specifications with piecewise time-varying…