papers

Publications (6)

cs.LG2026

Machine Unlearning under Retain-Forget Entanglement

Jingpu Cheng, Ping Liu, Qianxiao Li +1

Forgetting a subset in machine unlearning is rarely an isolated task. Often, retained samples that are closely related to the forget set can be unintentionally affected, particular…

cs.LG2026

Deep learning and the rate of approximation by flows

Jingpu Cheng, Qianxiao Li, Ting Lin +1

We investigate the dependence of the approximation capacity of deep residual networks on its depth in a continuous dynamical systems setting. This can be formulated as the general…

cs.LG2026

Closed-Form Concept Erasure via Double Projections

Chi Zhang, Jingpu Cheng, Zhixian Wang +1

While modern generative models such as diffusion-based architectures have enabled impressive creative capabilities, they also raise important safety and ethical risks. These concer…

cs.LG2025

Allocation of Parameters in Transformers

Ruoxi Yu, Haotian Jiang, Jingpu Cheng +3

Transformers have achieved remarkable successes across a wide range of applications, yet the theoretical foundation of their model efficiency remains underexplored. In this work, w…

cs.LG2025

A unified framework for establishing the universal approximation of transformer-type architectures

Jingpu Cheng, Ting Lin, Zuowei Shen +1

We investigate the universal approximation property (UAP) of transformer-type architectures, providing a unified theoretical framework that extends prior results on residual networ…

cs.LG2023

Interpolation, Approximation and Controllability of Deep Neural Networks

Jingpu Cheng, Qianxiao Li, Ting Lin +1

We investigate the expressive power of deep residual neural networks idealized as continuous dynamical systems through control theory. Specifically, we consider two properties that…