Niloofar Yousefi

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 …

FlowNIB: An Information Bottleneck Analysis of Bidirectional vs. Unidirectional Language Models

2025 · arXiv (Cornell University)

Bidirectional language models have better context understanding and perform better than unidirectional models on natural language understanding tasks, yet the theoretical reasons behind this advantage remain unclear. In this work, we investigate this disparity through …