Memorization and Optimization in Deep Neural Networks with Minimum Over-parameterization

20 May 2022

Papers citing "Memorization and Optimization in Deep Neural Networks with Minimum Over-parameterization"

8 / 8 papers shown

Title
Reparameterization invariance in approximate Bayesian inference Hrittik Roy M. Miani Carl Henrik Ek Philipp Hennig Marvin Pfortner Lukas Tatzel Søren Hauberg BDL 47 8 0 05 Jun 2024
Architectural Strategies for the optimization of Physics-Informed Neural Networks Hemanth Saratchandran Shin-Fang Chng Simon Lucey AI4CE 39 0 0 05 Feb 2024
Memorization Capacity of Multi-Head Attention in Transformers Sadegh Mahdavi Renjie Liao Christos Thrampoulidis 26 22 0 03 Jun 2023
How Spurious Features Are Memorized: Precise Analysis for Random and NTK Features Simone Bombari Marco Mondelli AAML 28 4 0 20 May 2023
Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent Kernels Simone Bombari Shayan Kiyani Marco Mondelli AAML 40 10 0 03 Feb 2023
On skip connections and normalisation layers in deep optimisation L. MacDonald Jack Valmadre Hemanth Saratchandran Simon Lucey ODL 19 1 0 10 Oct 2022
On the Proof of Global Convergence of Gradient Descent for Deep ReLU Networks with Linear Widths Quynh N. Nguyen 41 49 0 24 Jan 2021
Deep Networks and the Multiple Manifold Problem Sam Buchanan D. Gilboa John N. Wright 166 39 0 25 Aug 2020