4 papers
Adversarial Attacks Leverage Interference Between Features in Superposition
Edward Stevinson, Lucas Prieto, Melih Barsbey +1
Why do adversarial examples exist, and why do they transfer between models? Existing explanations appeal to high-dimensional geometry, non-robust patterns in the input, and decisio…
From Data Statistics to Feature Geometry: How Correlations Shape Superposition
Lucas Prieto, Edward Stevinson, Melih Barsbey +2
A central idea in mechanistic interpretability is that neural networks represent more features than they have dimensions, arranging them in superposition to form an over-complete b…
Large Learning Rates Simultaneously Achieve Robustness to Spurious Correlations and Compressibility
Melih Barsbey, Lucas Prieto, Stefanos Zafeiriou +1
Robustness and resource-efficiency are two highly desirable properties for modern machine learning models. However, achieving them jointly remains a challenge. In this paper, we id…
Grokking at the Edge of Numerical Stability
Lucas Prieto, Melih Barsbey, Pedro A. M. Mediano +1
Grokking, the sudden generalization that occurs after prolonged overfitting, is a surprising phenomenon challenging our understanding of deep learning. Although significant progres…