📐 Learning Theory

🎞️ ECCV2026 · 1 paper notes

📌 Same area in other venues: 🔬 ICLR2026 (293) · 🧪 ICML2026 (45) · 🤖 AAAI2026 (3) · 🧠 NeurIPS2025 (25) · 🧪 ICML2025 (16)

Pay Attention to Attention Distribution: A New Local Lipschitz Bound for Transformers

The paper incorporates attention probability distributions into a local bound on the self-attention Jacobian, uses tighter softmax spectral estimates to construct JaSMin regularization, and improves ViT-B accuracy under some adversarial attacks while exposing trade-offs among robustness, clean accuracy, and gradient propagation.