Search Results for author: Yuheng Bu

Found 14 papers, 1 papers with code

Tighter Expected Generalization Error Bounds via Convexity of Information Measures

no code implementations24 Feb 2022 Gholamali Aminian, Yuheng Bu, Gregory Wornell, Miguel Rodrigues

Due to the convexity of the information measures, the proposed bounds in terms of Wasserstein distance and total variation distance are shown to be tighter than their counterparts based on individual samples in the literature.

On the Benefits of Selectivity in Pseudo-Labeling for Unsupervised Multi-Source-Free Domain Adaptation

no code implementations1 Feb 2022 Maohao Shen, Yuheng Bu, Gregory Wornell

Due to privacy, storage, and other constraints, there is a growing need for unsupervised domain adaptation techniques in machine learning that do not require access to the data used to train a collection of source models.

Unsupervised Domain Adaptation

An Exact Characterization of the Generalization Error for the Gibbs Algorithm

no code implementations NeurIPS 2021 Gholamali Aminian, Yuheng Bu, Laura Toni, Miguel Rodrigues, Gregory Wornell

Various approaches have been developed to upper bound the generalization error of a supervised learning algorithm.

Characterizing and Understanding the Generalization Error of Transfer Learning with Gibbs Algorithm

no code implementations2 Nov 2021 Yuheng Bu, Gholamali Aminian, Laura Toni, Miguel Rodrigues, Gregory Wornell

We provide an information-theoretic analysis of the generalization ability of Gibbs-based transfer learning algorithms by focusing on two popular transfer learning approaches, $\alpha$-weighted-ERM and two-stage-ERM.

Transfer Learning

Selective Regression Under Fairness Criteria

no code implementations28 Oct 2021 Abhin Shah, Yuheng Bu, Joshua Ka-Wing Lee, Subhro Das, Rameswar Panda, Prasanna Sattigeri, Gregory W. Wornell

Selective regression allows abstention from prediction if the confidence to make an accurate prediction is not sufficient.

Fairness

A Maximal Correlation Approach to Imposing Fairness in Machine Learning

no code implementations30 Dec 2020 Joshua Lee, Yuheng Bu, Prasanna Sattigeri, Rameswar Panda, Gregory Wornell, Leonid Karlinsky, Rogerio Feris

As machine learning algorithms grow in popularity and diversify to many industries, ethical and legal concerns regarding their fairness have become increasingly relevant.

Fairness

Adaptive Sequential Machine Learning

no code implementations4 Apr 2019 Craig Wilson, Yuheng Bu, Venugopal Veeravalli

A framework previously introduced in [3] for solving a sequence of stochastic optimization problems with bounded changes in the minimizers is extended and applied to machine learning problems such as regression and classification.

Model Selection Stochastic Optimization

Information-Theoretic Understanding of Population Risk Improvement with Model Compression

1 code implementation27 Jan 2019 Yuheng Bu, Weihao Gao, Shaofeng Zou, Venugopal V. Veeravalli

We show that model compression can improve the population risk of a pre-trained model, by studying the tradeoff between the decrease in the generalization error and the increase in the empirical risk with model compression.

Model Compression

Tightening Mutual Information Based Bounds on Generalization Error

no code implementations15 Jan 2019 Yuheng Bu, Shaofeng Zou, Venugopal V. Veeravalli

The bound is derived under more general conditions on the loss function than in existing studies; nevertheless, it provides a tighter characterization of the generalization error.

Active Learning in Recommendation Systems with Multi-level User Preferences

no code implementations30 Nov 2018 Yuheng Bu, Kevin Small

While recommendation systems generally observe user behavior passively, there has been an increased interest in directly querying users to learn their specific preferences.

Active Learning Recommendation Systems

Model change detection with application to machine learning

no code implementations19 Nov 2018 Yuheng Bu, Jiaxun Lu, Venugopal V. Veeravalli

The goal is to detect whether the change in the model is significant, i. e., whether the difference between the pre-change parameter and the post-change parameter $\|\theta-\theta'\|_2$ is larger than a pre-determined threshold $\rho$.

Change Detection

Active and Adaptive Sequential learning

no code implementations29 May 2018 Yuheng Bu, Jiaxun Lu, Venugopal V. Veeravalli

Furthermore, an estimator of the change in the learning problems using the active learning samples is constructed, which provides an adaptive sample size selection rule that guarantees the excess risk is bounded for sufficiently large number of time steps.

Active Learning

Linear-Complexity Exponentially-Consistent Tests for Universal Outlying Sequence Detection

no code implementations21 Jan 2017 Yuheng Bu, Shaofeng Zou, Venugopal V. Veeravalli

A sequence is considered as outlying if the observations therein are generated by a distribution different from those generating the observations in the majority of the sequences.

Cannot find the paper you are looking for? You can Submit a new open access paper.