Most of the traditional pattern classifiers assume their input data to be well-behaved in terms of similar underlying class distributions, balanced size of classes, the presence of a full set of …
H Xu, S Mannor - Machine learning, 2012 - Springer
We derive generalization bounds for learning algorithms based on their robustness: the property that if a testing sample is “similar” to a training sample, then the testing error is close …
We consider regularized support vector machines (SVMs) and show that they are precisely equivalent to a new robust optimization formulation. We show that this equivalence of robust …
In this paper, we proposed a new robust twin support vector machine (called R-TWSVM) via second order cone programming formulations for classification, which can deal with data …
In this paper, we propose a primal-dual algorithm with a novel momentum term using the partial gradients of the coupling function that can be viewed as a generalization of the …
J Bi, T Zhang - Advances in neural information processing …, 2004 - proceedings.neurips.cc
This paper investigates a new learning model in which the input data is corrupted with noise. We present a general statistical framework to tackle this problem. Based on the statistical …
Motivated by the fact that there may be inaccuracies in features and labels of training data, we apply robust optimization techniques to study in a principled way the uncertainty in data …
B Dai, N He, Y Pan, B Boots… - Artificial Intelligence and …, 2017 - proceedings.mlr.press
Many machine learning tasks, such as learning with invariance and policy evaluation in reinforcement learning, can be characterized as problems of learning from conditional …
We propose a novel second order cone programming formulation for designing robust classifiers which can handle uncertainty in observations. Similar formulations are also …