activity
20242026
collaborators

6 papers

cs.LG2026

Geometric Analysis of Neural Regression Collapse via Intrinsic Dimension

George Andriopoulos, Zixuan Dong, Bimarsha Adhikari +1

Neural multivariate regression underpins a wide range of domains, including control, robotics, and finance, yet the geometry of its learned representations remains poorly character…

cs.LG2025

Neural Multivariate Regression: Qualitative Insights from the Unconstrained Feature Model

George Andriopoulos, Soyuj Jung Basnet, Juan Guevara +2

The Unconstrained Feature Model (UFM) is a mathematical framework that enables closed-form approximations for minimal training loss and related performance measures in deep neural…

cs.AI2025

Should We Ever Prefer Decision Transformer for Offline Reinforcement Learning?

Yumi Omori, Zixuan Dong, Keith Ross

In recent years, extensive work has explored the application of the Transformer architecture to reinforcement learning problems. Among these, Decision Transformer (DT) has gained p…

cs.LG2025

Minimal Ingredients for Reward Assignment from Expert Demonstrations

Zixuan Dong, Yumi Omori, Keith Ross

Reward assignment from scarce demonstrations is a key challenge in both offline and online imitation learning. A common and intuitive strategy assigns rewards according to how clos…

cs.LG2025

Cross Entropy versus Label Smoothing: A Neural Collapse Perspective

Li Guo, George Andriopoulos, Zifan Zhao +3

Label smoothing loss is a widely adopted technique to mitigate overfitting in deep neural networks. This paper studies label smoothing from the perspective of Neural Collapse (NC),…

cs.LG2024

The Prevalence of Neural Collapse in Neural Multivariate Regression

George Andriopoulos, Zixuan Dong, Li Guo +2

Recently it has been observed that neural networks exhibit Neural Collapse (NC) during the final stage of training for the classification problem. We empirically show that multivar…