AINeutralarXiv – CS AI · 7h ago6/10
🧠
Why Self-Supervised Encoders Want to Be Normal
Researchers develop a theoretical framework connecting Information Bottleneck principles to encoder-decoder learning through rate-distortion analysis, showing optimal representations form soft clusters on probability manifolds. The work introduces Sketched Isotropic Gaussian Regularization (SIGReg) as a principled regularizer for self-supervised, semi-supervised, and supervised learning without requiring variational bounds.