257 citations · 384 across the 11 of their papers we have counts for
7 papers · 1 filter
Sharper Analysis for Minibatch Stochastic Proximal Point Methods: Stability, Smoothness, and Deviation
Xiao-Tong Yuan, Ping Li
The stochastic proximal point (SPP) methods have gained recent attention for stochastic optimization, with strong convergence guarantees and superior robustness to the classic stoc…
On Convergence of FedProx: Local Dissimilarity Invariant Bounds, Non-smoothness and Beyond
Xiao-Tong Yuan, Ping Li
The FedProx algorithm is a simple yet powerful distributed proximal point optimization method widely used for federated learning (FL) over heterogeneous data. Despite its popularit…
Boosting the Confidence of Generalization for -Stable Randomized Learning Algorithms
Xiao-Tong Yuan, Ping Li
Exponential generalization bounds with near-tight rates have recently been established for uniformly stable learning algorithms. The notion of uniform stability, however, is string…
Stability and Risk Bounds of Iterative Hard Thresholding
Xiao-Tong Yuan, Ping Li
In this paper, we analyze the generalization performance of the Iterative Hard Thresholding (IHT) algorithm widely used for sparse recovery problems. The parameter estimation and s…
On Convergence of Distributed Approximate Newton Methods: Globalization, Sharper Bounds and Beyond
Xiao-Tong Yuan, Ping Li
The DANE algorithm is an approximate Newton method popularly used for communication-efficient distributed machine learning. Reasons for the interest in DANE include scalability and…
Learning Pairwise Graphical Models with Nonlinear Sufficient Statistics
Xiao-Tong Yuan, Ping Li, Tong Zhang
We investigate a generic problem of learning pairwise exponential family graphical models with pairwise sufficient statistics defined by a global mapping function, e.g., Mercer ker…
Truncated Power Method for Sparse Eigenvalue Problems
Xiao-Tong Yuan, Tong Zhang
This paper considers the sparse eigenvalue problem, which is to extract dominant (largest) sparse eigenvectors with at most non-zero components. We propose a simple yet effecti…