21 citations · 45 across the 9 of their papers we have counts for
7 papers · 1 filter
Evaluating the Representation Space of Diffusion Models via Self-Supervised Principles
Xiao Li, Yixuan Jia, Zekai Zhang +6
Diffusion models have demonstrated remarkable generative capabilities and have also emerged as powerful self-supervised representation learners, yet the connection between these tw…
An Illusion of Unlearning? Assessing Machine Unlearning Through Internal Representations
Yichen Gao, Altay Unal, Akshay Rangamani +1
While numerous machine unlearning (MU) methods have recently been developed with promising results in erasing the influence of forgotten data, classes, or concepts, they are also h…
Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modeling
Xiao Li, Zekai Zhang, Xiang Li +4
Diffusion models, though originally designed for generative tasks, have demonstrated impressive self-supervised representation learning capabilities. A particularly intriguing phen…
A Global Geometric Analysis of Maximal Coding Rate Reduction
Peng Wang, Huikang Liu, Druv Pai +4
The maximal coding rate reduction (MCR) objective for learning structured and compact deep representations is drawing increasing attention, especially after its recent usage in…
Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination
Peng Wang, Xiao Li, Can Yaras +4
Over the past decade, deep learning has proven to be a highly effective tool for learning meaningful features from raw data. However, it remains an open question how deep networks…
Generalized Neural Collapse for a Large Number of Classes
Jiachen Jiang, Jinxin Zhou, Peng Wang +4
Neural collapse provides an elegant mathematical characterization of learned last layer representations (a.k.a. features) and classifier weights in deep classification models. Such…
The Law of Parsimony in Gradient Descent for Learning Deep Linear Networks
Can Yaras, Peng Wang, Wei Hu +3
Over the past few years, an extensively studied phenomenon in training deep networks is the implicit bias of gradient descent towards parsimonious solutions. In this work, we inves…