We introduce and study minimax curriculum learning (MCL), a new method for adaptively
selecting a sequence of training subsets for a succession of stages in machine learning. The …

Curriculum learning is a technique to improve a model performance and generalization
based on the idea that easy samples should be presented before difficult ones during …

Curriculum Learning is motivated by human cognition, where teaching often involves
gradually exposing the learner to examples in a meaningful order, from easy to hard …

Curriculum learning (CL) is a commonly used machine learning training strategy. However,
we still lack a clear theoretical understanding of CL's benefits. In this paper, we study the …

The problem of machine teaching is considered. A new formulation is proposed under the
assumption of an optimal student, where optimality is defined in the usual machine learning …

Solving continuous minimax optimization is of extensive practical interest, yet notoriously
unstable and difficult. This paper introduces the learning to optimize (L2O) methodology to …

We provide theoretical investigation of curriculum learning in the context of stochastic
gradient descent when optimizing the convex linear regression loss. We prove that the rate …

Training machine learning models in a meaningful order, from the easy samples to the hard
ones, using curriculum learning can provide performance improvements over the standard …

Humans and animals learn much better when the examples are not randomly presented but
organized in a meaningful order which illustrates gradually more concepts, and gradually …

Training neural networks is traditionally done by providing a sequence of random mini-
batches sampled uniformly from the entire training data. In this work, we analyze the effect of …