Yunwen Lei

Local Rademacher Complexity-based Learning Guarantees for Multi-Task Learning

2016 · arXiv (Cornell University)

We show a Talagrand-type concentration inequality for Multi-Task Learning (MTL), using which we establish sharp excess risk bounds for MTL in terms of distribution- and data-dependent versions of the Local Rademacher Complexity (LRC). We also …

Fine-grained Generalization Analysis of Vector-Valued Learning

2021 · Proceedings of the AAAI Conference on Artificial Intelligence

Many fundamental machine learning tasks can be formulated as a problem of learning with vector-valued functions, where we learn multiple scalar-valued functions together. Although there is some generalization analysis on different specific algorithms under the …

Differentially Private SGDA for Minimax Problems

2022 · arXiv (Cornell University)

Stochastic gradient descent ascent (SGDA) and its variants have been the workhorse for solving minimax problems. However, in contrast to the well-studied stochastic gradient descent (SGD) with differential privacy (DP) constraints, there is little work …

Multi-class SVMs: From Tighter Data-Dependent Generalization Bounds to Novel Algorithms

2015 · arXiv (Cornell University)

This paper studies the generalization performance of multi-class classification algorithms, for which we obtain, for the first time, a data-dependent generalization error bound with a logarithmic dependence on the class size, substantially improving the state-of-the-art …