← Search

Pengjun Chen

2 accepted papers

2026

Understanding and Enhancing Differentiable Architecture Search from Information Bottleneck Perspective

AAAI 2026technical

Performance collapse is an intractable issue of Differentiable Architecture Search (DAS), where severe performance degradation of DAS happens when it trains on different search spaces or datasets. We theoretically analyze the issue from the information bottleneck (IB) perspective, and disclose that

Cited by 0SourcePDFScholar
2025

Beyond the Limits: Overcoming Negative Correlation of Activation-Based Training-Free NAS

ICCV 2025poster

Training-free Neural Architecture Search (NAS) has emerged an efficient way to discover high-performing lightweight models with zero-cost proxies (e.g., the activation-based proxies (AZP)). In this paper, we observe a new negative correlation phenomenon that the correlations of the AZP dramatically…

Cited by 0SourcePDFScholar