collaborators

6 papers

cs.LG2026

Optimized Deferral for Imbalanced Settings

Corinna Cortes, Anqi Mao, Mehryar Mohri +1

Learning algorithms can be significantly improved by routing complex or uncertain inputs to specialized experts, balancing accuracy with computational cost. This approach, known as…

cs.LG2025

Principled Algorithms for Optimizing Generalized Metrics in Binary Classification

Anqi Mao, Mehryar Mohri, Yutao Zhong

In applications with significant class imbalance or asymmetric costs, metrics such as the -measure, AM measure, Jaccard similarity coefficient, and weighted accuracy offer mo…

cs.LG2025

Mastering Multiple-Expert Routing: Realizable -Consistency and Strong Guarantees for Learning to Defer

Anqi Mao, Mehryar Mohri, Yutao Zhong

The problem of learning to defer with multiple experts consists of optimally assigning input instances to experts, balancing the trade-off between their accuracy and computational…

cs.LG2025

Balancing the Scales: A Theoretical and Algorithmic Framework for Learning from Imbalanced Data

Corinna Cortes, Anqi Mao, Mehryar Mohri +1

Class imbalance remains a major challenge in machine learning, especially in multi-class problems with long-tailed distributions. Existing methods, such as data resampling, cost-se…

cs.LG2025

Theory and Algorithms for Learning with Multi-Class Abstention and Multi-Expert Deferral

Anqi Mao

Large language models (LLMs) have achieved remarkable performance but face critical challenges: hallucinations and high inference costs. Leveraging multiple experts offers a soluti…

cs.LG2025

Enhanced -Consistency Bounds

Anqi Mao, Mehryar Mohri, Yutao Zhong

Recent research has introduced a key notion of -consistency bounds for surrogate losses. These bounds offer finite-sample guarantees, quantifying the relationship between the ze…