$The boundary of neural network trainability is fractal$

The boundary of neural network trainability is fractal

9 February 2024

Jascha Narain Sohl-Dickstein

Papers citing "The boundary of neural network trainability is fractal"

5 / 5 papers shown

Title
FOCUS: First Order Concentrated Updating Scheme Yizhou Liu Ziming Liu Jeff Gore ODL 104 0 0 21 Jan 2025
Mapping the Edge of Chaos: Fractal-Like Boundaries in The Trainability of Decoder-Only Transformer Models Bahman Torkamandi AI4CE 35 0 0 08 Jan 2025
A spring-block theory of feature learning in deep neural networks Chengzhi Shi Liming Pan Ivan Dokmanić AI4CE 33 1 0 28 Jul 2024
Robustness of Algorithms for Causal Structure Learning to Hyperparameter Choice Damian Machlanski Spyridon Samothrakis Paul Clarke CML 17 1 0 27 Oct 2023
From Stability to Chaos: Analyzing Gradient Descent Dynamics in Quadratic Regression Xuxing Chen Krishnakumar Balasubramanian Promit Ghosal Bhavya Agrawalla 28 7 0 02 Oct 2023