218 citations · 265 across the 23 of their papers we have counts for
23 papers
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…
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 mor…
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…
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…
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…
Multi-Label Learning with Stronger Consistency Guarantees
Anqi Mao, Mehryar Mohri, Yutao Zhong
We present a detailed study of surrogate losses and algorithms for multi-label learning, supported by -consistency bounds. We first show that, for the simplest form of multi-lab…
Realizable -Consistent and Bayes-Consistent Loss Functions for Learning to Defer
Anqi Mao, Mehryar Mohri, Yutao Zhong
We present a comprehensive study of surrogate loss functions for learning to defer. We introduce a broad family of surrogate losses, parameterized by a non-increasing function ,…
Cardinality-Aware Set Prediction and Top- Classification
Corinna Cortes, Anqi Mao, Christopher Mohri +2
We present a detailed study of cardinality-aware top- classification, a novel approach that aims to learn an accurate top- set predictor while maintaining a low cardinality.…
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…
A Universal Growth Rate for Learning with Smooth Surrogate Losses
Anqi Mao, Mehryar Mohri, Yutao Zhong
This paper presents a comprehensive analysis of the growth rate of -consistency bounds (and excess error bounds) for various surrogate losses used in classification. We prove a…
Top- Classification and Cardinality-Aware Prediction
Anqi Mao, Mehryar Mohri, Yutao Zhong
We present a detailed study of top- classification, the task of predicting the most probable classes for an input, extending beyond single-class prediction. We demonstrate t…
Regression with Multi-Expert Deferral
Anqi Mao, Mehryar Mohri, Yutao Zhong
Learning to defer with multiple experts is a framework where the learner can choose to defer the prediction to several experts. While this problem has received significant attentio…
-Consistency Guarantees for Regression
Anqi Mao, Mehryar Mohri, Yutao Zhong
We present a detailed study of -consistency bounds for regression. We first present new theorems that generalize the tools previously given to establish -consistency bounds.…
Principled Approaches for Learning to Defer with Multiple Experts
Anqi Mao, Mehryar Mohri, Yutao Zhong
We present a study of surrogate losses and algorithms for the general problem of learning to defer with multiple experts. We first introduce a new family of surrogate losses specif…
Predictor-Rejector Multi-Class Abstention: Theoretical Analysis and Algorithms
Anqi Mao, Mehryar Mohri, Yutao Zhong
We study the key framework of learning with abstention in the multi-class classification setting. In this setting, the learner can choose to abstain from making a prediction with s…
Theoretically Grounded Loss Functions and Algorithms for Score-Based Multi-Class Abstention
Anqi Mao, Mehryar Mohri, Yutao Zhong
Learning with abstention is a key scenario where the learner can abstain from making a prediction at some cost. In this paper, we analyze the score-based formulation of learning wi…
Ranking with Abstention
Anqi Mao, Mehryar Mohri, Yutao Zhong
We introduce a novel framework of ranking with abstention, where the learner can abstain from making prediction at some limited cost . We present a extensive theoretical analysi…
Differentially Private Domain Adaptation with Theoretical Guarantees
Raef Bassily, Corinna Cortes, Anqi Mao +1
In many applications, the labeled data at the learner's disposal is subject to privacy constraints and is relatively limited. To derive a more accurate predictor for the target dom…
Cross-Entropy Loss Functions: Theoretical Analysis and Applications
Anqi Mao, Mehryar Mohri, Yutao Zhong
Cross-entropy is a widely used loss function in applications. It coincides with the logistic loss applied to the outputs of a neural network, when the softmax is used. But, what gu…
-Consistency Estimation Error of Surrogate Loss Minimizers
Pranjal Awasthi, Anqi Mao, Mehryar Mohri +1
We present a detailed study of estimation errors in terms of surrogate loss estimation errors. We refer to such guarantees as -consistency estimation error bounds, sin…
A Finer Calibration Analysis for Adversarial Robustness
Pranjal Awasthi, Anqi Mao, Mehryar Mohri +1
We present a more general analysis of -calibration for adversarially robust classification. By adopting a finer definition of calibration, we can cover settings beyond the restr…
Calibration and Consistency of Adversarial Surrogate Losses
Pranjal Awasthi, Natalie Frank, Anqi Mao +2
Adversarial robustness is an increasingly critical property of classifiers in applications. The design of robust algorithms relies on surrogate losses since the optimization of the…
Variational training of neural network approximations of solution maps for physical models
Yingzhou Li, Jianfeng Lu, Anqi Mao
A novel solve-training framework is proposed to train neural network in representing low dimensional solution maps of physical models. Solve-training framework uses the neural netw…