3 papers
stat.ML2026
Stability beyond Bounded Differences: Sharp Generalization Bounds under Finite Moments
Qianqian Lei, Soham Bonnerjee, Yuefeng Han +1
While algorithmic stability is a central tool for understanding generalization of learning algorithms, existing high-probability guarantees typically rely on uniform boundedness or…
stat.ML2026
Refining Covariance Matrix Estimation in Stochastic Gradient Descent Through Bias Reduction
Ziyang Wei, Wanrong Zhu, Jingyang Lyu +1
We study online inference and asymptotic covariance estimation for the stochastic gradient descent (SGD) algorithm. While classical methods (such as plug-in and batch-means estimat…
stat.ML2026
Sharp asymptotic theory for Q-learning with LDTZ learning rate and its generalization
Soham Bonnerjee, Zhipeng Lou, Wei Biao Wu
Despite the sustained popularity of Q-learning as a practical tool for policy determination, a majority of relevant theoretical literature deals with either constant ($η_{t}\equiv…