Results 1 -
5 of
5
The teaching dimension of linear learners.
- In Proceedings of The 33rd International Conference on Machine Learning, ICML ’16,
, 2016
"... Abstract Teaching dimension is a learning theoretic quantity that specifies the minimum training set size to teach a target model to a learner. Previous studies on teaching dimension focused on version-space learners which maintain all hypotheses consistent with the training data, and cannot be app ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
(Show Context)
Abstract Teaching dimension is a learning theoretic quantity that specifies the minimum training set size to teach a target model to a learner. Previous studies on teaching dimension focused on version-space learners which maintain all hypotheses consistent with the training data, and cannot be applied to modern machine learners which select a specific hypothesis via optimization. This paper presents the first known teaching dimension for ridge regression, support vector machines, and logistic regression. We also exhibit optimal training sets that match these teaching dimensions. Our approach generalizes to other linear learners.
The Security of Latent Dirichlet Allocation
"... Latent Dirichlet allocation (LDA) is an in-creasingly popular tool for data analysis in many domains. If LDA output affects de-cision making (especially when money is in-volved), there is an incentive for attackers to compromise it. We ask the question: how can an attacker minimally poison the corpu ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
(Show Context)
Latent Dirichlet allocation (LDA) is an in-creasingly popular tool for data analysis in many domains. If LDA output affects de-cision making (especially when money is in-volved), there is an incentive for attackers to compromise it. We ask the question: how can an attacker minimally poison the corpus so that LDA produces topics that the attacker wants the LDA user to see? Answering this question is important to characterize such at-tacks, and to develop defenses in the future. We give a novel bilevel optimization formu-lation to identify the optimal poisoning at-tack. We present an efficient solution (up to local optima) using descent method and im-plicit functions. We demonstrate poisoning attacks on LDA with extensive experiments, and discuss possible defenses. 1
Becoming the Expert- Interactive Multi-Class Machine Teaching
"... Compared to machines, humans are extremely good at classifying images into categories, especially when they possess prior knowledge of the categories at hand. If this prior information is not available, supervision in the form of teaching images is required. To learn categories more quickly, people ..."
Abstract
- Add to MetaCart
(Show Context)
Compared to machines, humans are extremely good at classifying images into categories, especially when they possess prior knowledge of the categories at hand. If this prior information is not available, supervision in the form of teaching images is required. To learn categories more quickly, people should see important and representative im-ages first, followed by less important images later – or not at all. However, image-importance is individual-specific, i.e. a teaching image is important to a student if it changes their overall ability to discriminate between classes. Further, stu-dents keep learning, so while image-importance depends on their current knowledge, it also varies with time. In this work we propose an Interactive Machine Teach-ing algorithm that enables a computer to teach challeng-ing visual concepts to a human. Our adaptive algorithm chooses, online, which labeled images from a teaching set should be shown to the student as they learn. We show that a teaching strategy that probabilistically models the student’s ability and progress, based on their correct and incorrect answers, produces better ‘experts’. We present results us-ing real human participants across several varied and chal-lenging real-world datasets. 1.
Analysis of a Design Pattern for Teaching with Features and Labels
"... Abstract We study the task of teaching a machine to classify objects using features and labels. We introduce the Error-Driven-Featuring design pattern for teaching using features and labels in which a teacher prefers to introduce features only if they are needed. We analyze the potential risks and ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract We study the task of teaching a machine to classify objects using features and labels. We introduce the Error-Driven-Featuring design pattern for teaching using features and labels in which a teacher prefers to introduce features only if they are needed. We analyze the potential risks and benefits of this teaching pattern through the use of teaching protocols, illustrative examples, and by providing bounds on the effort required for an optimal machine teacher using a linear learning algorithm, the most commonly used type of learners in interactive machine learning systems. Our analysis provides a deeper understanding of potential trade-offs of using different learning algorithms and between the effort required for featuring and labeling.
Some Submodular Data-Poisoning Attacks on Machine Learners
, 2015
"... We study data-poisoning attacks using a machine teaching framework. For a family of NP-hard attack problems we pose them as submodular function maximization, thereby inheriting efficient greedy algorithms with theoretical guarantees. We demonstrate some attacks with experiments. 1 ..."
Abstract
- Add to MetaCart
(Show Context)
We study data-poisoning attacks using a machine teaching framework. For a family of NP-hard attack problems we pose them as submodular function maximization, thereby inheriting efficient greedy algorithms with theoretical guarantees. We demonstrate some attacks with experiments. 1
