Provable Advantage of Curriculum Learning on Parity Targets with Mixed Inputs

29 June 2023

Papers citing "Provable Advantage of Curriculum Learning on Parity Targets with Mixed Inputs"

11 / 11 papers shown

Title
Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions Elisabetta Cornacchia Dan Mikulincer Elchanan Mossel 86 1 0 10 Feb 2025
Optimal Protocols for Continual Learning via Statistical Physics and Control Theory Francesco Mori Stefano Sarao Mannelli Francesca Mignacco 80 3 0 26 Sep 2024
On the non-universality of deep learning: quantifying the cost of symmetry Emmanuel Abbe Enric Boix-Adserà FedML MLT 40 18 0 05 Aug 2022
Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit Boaz Barak Benjamin L. Edelman Surbhi Goel Sham Kakade Eran Malach Cyril Zhang 57 126 0 18 Jul 2022
An initial alignment between neural network and target is needed for gradient descent to learn Emmanuel Abbe Elisabetta Cornacchia Jan Hązła Christopher Marquis 57 16 0 25 Feb 2022
An Analytical Theory of Curriculum Learning in Teacher-Student Networks Luca Saglietti Stefano Sarao Mannelli Andrew M. Saxe 34 25 0 15 Jun 2021
Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels Eran Malach Pritish Kamath Emmanuel Abbe Nathan Srebro 34 39 0 01 Mar 2021
Online Stochastic Gradient Descent with Arbitrary Initialization Solves Non-smooth, Non-convex Phase Retrieval Yan Shuo Tan Roman Vershynin 43 35 0 28 Oct 2019
On The Power of Curriculum Learning in Training Deep Networks Guy Hacohen D. Weinshall ODL 50 443 0 07 Apr 2019
Competence-based Curriculum Learning for Neural Machine Translation Emmanouil Antonios Platanios Otilia Stretcu Graham Neubig Barnabás Póczós Tom Michael Mitchell 43 340 0 23 Mar 2019
An Empirical Exploration of Curriculum Learning for Neural Machine Translation Xuan Zhang Manish Kumar Huda Khayrallah Kenton W. Murray Jeremy Gwinnup Marianna J. Martindale Paul McNamee Kevin Duh Marine Carpuat ODL 49 110 0 02 Nov 2018