COMS 6998 : Advanced Complexity Spring 2017 Lecture 2 : January 26 , 2017

COMS 6998 - 4 Fall 2017 Presenter : Geelon So

Recall that in the active learning setting, learner is provided with unlabeled samples, and can query teacher for the label. The goal is to learn a concept close enough to the target concept while minimizing the number of labels queried. Ideally the number of labels needed is much smaller than Ω(1/ ), which is the number of labeled examples in the passive learning setting. To characterize the s...

Notes for COMS 6998-4 Fall 2017

COMS 6998 - 4 Fall 2017 Presenter : Wenxi Chen

This lecture is delivered in more philosophical sense rather than technically. In the past, we have learned a series of algorithms which can dig deeper in a training dataset and generate a model based on such a dataset. However, without knowing of what knowledge is contained in the model, it is generally hard for human beings to trust the trained model and apply it in reality. Sometimes, biased...

COMS 6998 - 4 Fall 2017 Presenter : Geelon So

In the setting of active learning, the data comes unlabeled and querying the label of a data point is expensive. The goal of an active learner is to reduce the number of labels needed and output a hypothesis with error rate ≤ . Recall that the usual sample complexity of supervised learning is Ω(1/ ). The motivation for defining splitting index is to characterize the sample complexity of active ...

COMS E 6998 : Algorithmic Game Theory and Economics Jan 27 , 2011 Lecture 2 – Congestion Games

Last week we looked at a global network connection game, and used the potential function method to show the existence of a global potential function and a pure equilibrium for that game. This week we will broaden our focus to the generalization of this game, which is the category of the Congestion Games. These games are of interest because they model many network, routing and resource allocatio...