arXiv Machine Learning

Dropout Universality: Scaling Laws and Optimal Scheduling at the Edge-of-Chaos

arXiv:2605. 21648v2 Announce Type: replace Abstract: We develop a mean-field theory of dropout as a perturbation of critical signal propagation at the edge of chaos, and show that it predicts a simple, no-cost change to standard practice: \emph{front-loaded} dropout schedules cut test loss by \(18\)--\(35\%\) over constant dropout in MLPs and Vision Transformers at fixed budget.

Hugging Face Trending Papers
Jun 9

Rank Collapse, Fixed Points, and the Renormalization Group Structure of MLP Residual Networks

The analogy between deep neural network forward passes and renormalization group (RG) flows has been repeatedly noted in the literature, but existing treatments remain qualitative: depth is described as a coarse-graining scale, attention is likened to a partition function, and representations are said to flow toward fixed points. No existing work has defined a measurable RG order parameter, tested it under controlled variation of the input distribution, or made quantitative predictions that are empirically verified.

arXiv Machine Learning
Jun 10

Rank Collapse, Fixed Points, and the Renormalization Group Structure of MLP Residual Networks

arXiv:2606. 10324v1 Announce Type: new Abstract: The analogy between deep neural network forward passes and renormalization group (RG) flows has been repeatedly noted in the literature, but existing treatments remain qualitative: depth is described as a coarse-graining scale, attention is likened to a partition function, and representations are said to flow toward fixed points.

By Parviz Haggi-Mani, Irina Rish
Hugging Face Trending Papers
Jul 15

Transforming Rank: How Architecture Navigates the Spectral Pathologies of Depth

We investigate how each component of the Transformer feedforward block architecture design determines how much rank survives across depth at initialization. We reinterpret skip connections and normalization, long understood as controlling magnitude, as mechanisms for preserving gradient rank across depth, since the very matrix multiplications and nonlinear activations that make the network expressive also reduce the rank.

arXiv AI
Jul 16

DeepLoop: Depth Scaling for Looped Transformers

arXiv:2607. 13491v1 Announce Type: cross Abstract: Looped Transformers scale sequential computation by applying a compact stack of physical blocks for multiple rounds, increasing unrolled depth without increasing stored parameters.

By Shuzhen Li, Yifan Zhang, Jiacheng Guo, Quanquan Gu, Mengdi Wang