A Provably Correct Algorithm for Deep Learning that Actually Works

26 March 2018

Papers citing "A Provably Correct Algorithm for Deep Learning that Actually Works"

9 / 9 papers shown

Title
Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Francesco Cagnetta Alessandro Favero Antonio Sclocchi M. Wyart 30 0 0 11 May 2025
Learning curves theory for hierarchically compositional data with power-law distributed features Francesco Cagnetta Hyunmo Kang M. Wyart 38 0 0 11 May 2025
Probing the Latent Hierarchical Structure of Data via Diffusion Models Antonio Sclocchi Alessandro Favero Noam Itzhak Levi M. Wyart DiffM 35 3 0 17 Oct 2024
Training Deep Architectures Without End-to-End Backpropagation: A Survey on the Provably Optimal Methods Shiyu Duan José C. Príncipe MQ 38 3 0 09 Jan 2021
Why Layer-Wise Learning is Hard to Scale-up and a Possible Solution via Accelerated Downsampling Wenchi Ma Miao Yu Kaidong Li Guanghui Wang 14 5 0 15 Oct 2020
Computational Separation Between Convolutional and Fully-Connected Networks Eran Malach Shai Shalev-Shwartz 24 26 0 03 Oct 2020
From Boltzmann Machines to Neural Networks and Back Again Surbhi Goel Adam R. Klivans Frederic Koehler 19 5 0 25 Jul 2020
Training Neural Networks with Local Error Signals Arild Nøkland L. Eidnes 32 226 0 20 Jan 2019
End-to-end Learning of a Convolutional Neural Network via Deep Tensor Decomposition Samet Oymak Mahdi Soltanolkotabi 21 12 0 16 May 2018