6 papers
-Based Adaptive Identification under Quantized Observations with Applications
Xin Zheng, Yifei Jin, Yujing Liu +1
Quantized observations are ubiquitous in a wide range of applications across engineering and the social sciences, and algorithms based on the -norm are well recognized for…
Analysis of Adam Algorithms for Stochastic Dynamic Systems
Xin Zheng, Yifei Jin, Lei Guo
The adaptive moment estimation algorithm, known as Adam, is widely used in modern machine learning, owing to its low per-iteration complexity and strong empirical performance. Desp…
Momentum LMS Theory beyond Stationarity: Stability, Tracking, and Regret
Yifei Jin, Xin Zheng, Lei Guo
In large-scale data processing scenarios, data often arrive in sequential streams generated by complex systems that exhibit drifting distributions and time-varying system parameter…
Gradient-Based Adaptive Prediction and Control for Nonlinear Dynamical Systems
Yujing Liu, Xin Zheng, Zhixin Liu +1
This paper investigates gradient-based adaptive prediction and control for nonlinear stochastic dynamical systems under a weak convexity condition on the prediction-based loss. Thi…
Adaptive Sentencing Prediction with Guaranteed Accuracy and Legal Interpretability
Yifei Jin, Xin Zheng, Lei Guo
Existing research on judicial sentencing prediction predominantly relies on end-to-end models, which often neglect the inherent sentencing logic and lack interpretability-a critica…
-Based Adaptive Identification with Saturated Observations
Xin Zheng, Lei Guo
It is well-known that saturated output observations are prevalent in various practical systems and that the -norm is more robust than the -norm-based parameter esti…