Neural Collapse in Deep Linear Networks: From Balanced to Imbalanced Data
Jul 24, 2023
Sprecher:innen
Stanley Osher
Sprecher:in · 0 Follower:innen
Hung Tran-The
Sprecher:in · 0 Follower:innen
Tan Minh Nguyen
Sprecher:in · 0 Follower:innen
Über
Modern deep neural networks have achieved impressive performance on tasks from image classification to natural language processing. Surprisingly, these complex systems with massive amounts of parameters exhibit the same structural properties in their last-layer features and classifiers across canonical datasets when training until convergence. In particular, it has been observed that the last-layer features collapse to their class-means, and those class-means are the vertices of a simplex Equiangular Tight Frame (ETF). This phenomenon is known as Neural Collapse (NC). Recent papers have theoretically shown that NC emerges in the global minimizers of training problems with the simplified “unconstrained feature model”. In this context, we take a step further and prove the NC occurrences in deep linear networks for the popular mean squared error (MSE) and cross entropy (CE) losses, showing that global solutions exhibit NC properties across the linear layers. Furthermore, we extend our study to imbalanced data for MSE loss and present the first geometric analysis of NC under bias-free setting. Our results demonstrate the convergence of the last-layer features and classifiers to a geometry consisting of orthogonal vectors, whose lengths depend on the amount of data in their corresponding classes. Finally, we empirically validate our theoretical analyses on synthetic and practical network architectures with both balanced and imbalanced scenarios.Modern deep neural networks have achieved impressive performance on tasks from image classification to natural language processing. Surprisingly, these complex systems with massive amounts of parameters exhibit the same structural properties in their last-layer features and classifiers across canonical datasets when training until convergence. In particular, it has been observed that the last-layer features collapse to their class-means, and those class-means are the vertices of a simplex Equian…
Gefällt euch das Format? Vertraut auf SlidesLive, um euer nächstes Event festzuhalten!
Professionelle Aufzeichnung und Livestreaming – weltweit.
Freigeben
Empfohlene Videos
Präsentationen, deren Thema, Kategorie oder Sprecher:in ähnlich sind
Wasserstein Barycenter Matching for Graph Size Generalization of Message Passing Neural Networks
Später ansehen
Xu Chu, …
Gradient-Based Methods for Discrete Sampling
Später ansehen
DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution Models
Später ansehen
Liangbin Xie, …
Exponential Smoothing for Off-Policy Learning
Später ansehen
Imad Aouali, …
Differentially Private Sharpness-Aware Training
Später ansehen
