collaborators

5 papers

cs.LG2026

Invertible Logits Transformation for Accuracy-Preserving Post-Hoc Uncertainty Calibration

Lening Zhao, Qipeng Zhan, Li Shen

Post-hoc calibration aligns a classifier's predicted confidences with its empirical accuracy without retraining. An ideal calibrator should correct nonlinear miscalibration, scale…

cs.LG2026

Generative Cross-Entropy: A Strictly Proper Loss for Data-Efficient Classification

Qipeng Zhan, Zhuoping Zhou, Li Shen

Cross-entropy (CE) is the default training loss for supervised classification, but its sample efficiency is limited when labels are scarce. Existing remedies primarily act on the d…

cs.LG2026

Bi-Lipschitz Autoencoder With Injectivity Guarantee

Qipeng Zhan, Zhuoping Zhou, Zexuan Wang +2

Autoencoders are widely used for dimensionality reduction, based on the assumption that high-dimensional data lies on low-dimensional manifolds. Regularized autoencoders aim to pre…

cs.LG2026

PCAE: Learning Ordered Representations in Latent Space for Intrinsic Dimension Estimation via Principal Component Autoencoder

Qipeng Zhan, Zhuoping Zhou, Zexuan Wang +1

Autoencoders have long been considered a nonlinear extension of Principal Component Analysis (PCA). Prior studies have demonstrated that linear autoencoders (LAEs) can recover the…

cs.LG2025

Multi-Scale Geometric Autoencoder

Qipeng Zhan, Zhuoping Zhou, Zexuan Wang +1

Autoencoders have emerged as powerful models for visualization and dimensionality reduction based on the fundamental assumption that high-dimensional data is generated from a low-d…