scientific article; zbMATH DE number 7306907

MaRDI QIDQ5149018zbMATH OpenFDO

Authors Daphna Weinshall, Dan Amir

Publication date 5 February 2021

Full work available at URL https://arxiv.org/abs/1812.03472, https://jmlr.csail.mit.edu/papers/v21/18-751.html

zbMATH Keywords

curriculum learninghinge loss minimizationlinear regression

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Learning with convex loss and indefinite kernels
• Learning Curves for Stochastic Gradient Descent in Linear Feedforward Networks
• The importance of convexity in learning with squared loss
• Iterative regularization for learning with convex loss functions
• Optimal learning with Gaussians and correntropy loss
• On Bayesian learning via loss functions
• Learning curves for LMS and regular Gaussian processes
• scientific article; zbMATH DE number 19772
• From inexact optimization to learning via gradient concentration

Cites work

• Boosting the margin: a new explanation for the effectiveness of voting methods

Cited in

(6)

• On learning to become a successful loser: A comparison of alternative abstractions of learning processes in the loss domain
• The importance of convexity in learning with squared loss
• An analytical theory of curriculum learning in teacher–student networks*
• Heuristic search of optimal machine teaching curricula
• Tilting the odds at the lottery: the interplay of overparameterisation and curricula in neural networks
• Optimal protocols for continual learning via statistical physics and control theory

Describes a project that uses

Uses Software

• FaceNet

This page was built for publication:

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5149018)