15 citations · 15 across the 2 of their papers we have counts for
5 papers · 1 filter
Stochastic Gradient Descent: A Nonlinear Time Series Perspective
Jiaqi Li, Zhipeng Lou, Stefan Richter +1
This paper investigates the statistical behavior of Stochastic Gradient Descent (SGD) with constant step size under the framework of iterated random functions. Compared to previous…
A Nonlinear Time-Series Theory for Constant-step SGD with Momentum
Younghun Lee, Jake Zummo, Wei Biao Wu
Constant-step stochastic gradient descent with momentum (SGDM) augments the parameter recursion with a momentum state that carries geometrically decaying memory of past stochastic…
When Does Trust Help? A Leakage-Free Evaluation of Representation- and Aggregation-Based Defenses Against Backdoors in Federated Intrusion Detection
Shiddarth Dey Tusar, Zawad Yalmie Sazid
Federated learning (FL) lets distributed intrusion-detection systems (IDS) train on private traffic, but exposes the global model to poisoning and backdoor attacks under non-IID cl…
Finite-Sample Distribution Theory and Efficient Large-Scale Inference for Online Quantile Regression
Ziyang Wei, Jiaqi Li, Lan Wang +1
This paper studies online quantile regression for large-scale and streaming data using Stochastic SubGradient Descent (SSGD) with constant learning rates. Classical offline inferen…
Moment-Accurate Gaussian Mixtures for Constant-Step Stochastic Approximation
Xiaoli Li, Wei Biao Wu
Local Gaussian models of constant-step learning predict output variability and expected losses, but weak convergence alone does not justify these moment predictions. We establish m…