This paper surveys the machine learning literature and presents in an optimization
framework several commonly used machine learning approaches. Particularly …

We study a novel curriculum learning scheme where in each round, samples are selected to
achieve the greatest progress and fastest learning speed towards the ground-truth on all …

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 …

We consider the scalable recognition problem in the fine-grained expert domain where large-
scale data collection is easy whereas annotation is difficult. Existing solutions are typically …

In human pedagogy, teachers and students can interact adaptively to maximize
communication efficiency. The teacher adjusts her teaching method for different students …

In this paper, we propose the first machine teaching algorithm for multiple inverse
reinforcement learners. As our initial contribution, we formalize the problem of optimally …

In some crowdsourcing projects, such as citizen science, workers often participate for a long
period of time and thus improving their skills is an important issue. Recently, self-correction …

Our goal is to understand and optimize human concept learning by predicting the ease of
learning of a particular exemplar or category. We propose a method for estimating ease …

개념 및 범주 학습은 지식을 적용하고 확장하는 데 필수적인 과정으로, 학습자는 효과적인 범주
학습전략을 잘 알고 활용할 수 있어야 한다. 본 연구는 선행연구에서 효과성이 검증된 6 개의 …

This thesis provides an overview of recent results in adversarial online learning due to
myself and my collaborators. The key question is the following: Consider an online learning …