Robust Classification with Interval Data

By Laurent El Ghaoui, Gert R. G. Lanckriet. 2003

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Using Machine Teaching to Identify Optimal Training-Set Attacks on Machine Learners (2015, background): “There is a related line of research on robust learning [15, 25, 13, 28, 16, 12].”
Convex Adversarial Collective Classification (2013, methodology): “This results in a zero-sum game between the learner and adversary that can be solved using robust minimax methods as in [10, 20, 21, 22].”
On Robustness and Regularization of Structural Support Vector Machines (2014, background): “A number of other authors have explored the application of robust optimization to classification problems (e.g., (Lanckriet et al., 2003; El Ghaoui et al., 2003; Bhattacharyya et al., 2004; Shivaswamy et al., 2006)).”
Classifier evaluation and attribute selection against active adversaries (2010, methodology): “In that case, the Stackelberg solution concept for adversarial classification corresponds to the minimax solution studied in depth by many authors (Lanckriet et al. 2003; El Ghaoui et al. 2003).”
Bayesian Games for Adversarial Regression Problems (2013, background): “Globerson & Roweis (2006) study the case of features that are deleted at test time; El Ghaoui et al. (2003) study features that are changed within an interval.”
Robust Optimization (2021, background): “Support vector machines with interval uncertainty (and their connections to sparse classification) are studied in [51], while the case with ellipsoidal uncertainty on the data points has been introduced and applied in a biology context in [29].”
Self-regularity - a new paradigm for primal-dual interior-point algorithms (2002, background): “Support vector machines with interval uncertainty (and their connections to sparse classification) are studied in [51], while the case with ellipsoidal uncertainty on the data points has been introduced and applied in a biology context in [29].”
Feature Cross-Substitution in Adversarial Classification (2014, background): “We show that our algorithmic approach significantly outperforms state-of-the-art alternatives.”
Nash Equilibria of Static Prediction Games (2009, methodology): “El Ghaoui et al. [2] study a minimax model for input data that are known to lie within some hyper-rectangle.”
A Simple Geometric Interpretation of SVM using Stochastic Adversaries (2012, background): “Unlike previous approaches for robust classification [12, 13, 10] we focus on perturbations that are stochastic in nature and not deterministic.”
Explicit Defense Actions Against Test-Set Attacks (2017, background): “Robust Learning (Globerson and Roweis 2006; El Ghaoui et al. 2003) considers the setting where a test set is drawn from a distribution distinct from the training set’s.”
Nightmare at test time: robust learning by feature deletion (2006, background): “Our approach is related to (El Ghaoui et al., 2003) where the location of sample points is only known up to an ellipsoidal region, and a classiﬂer that is optimal in the worst case is sought.”
Theory and Applications of Robust Optimization (2010, methodology): “[55] considers an interval uncertainty model for X: X (ρ) = {Z ∈ Rn×N | X − ρΣ ≤ Z ≤ X + ρΣ} , (4.”
Robust Classification (2019, methodology): “We note that similar results on more specific uncertainty sets have been previously shown in El Ghaoui et al. (2003) and Harrington et al. (2010). Theorem 2.”
Stackelberg games for adversarial prediction problems (2011, unknown): “[5] derive a minimax model for input data that are known to lie within some hyper-rectangles around the training instances.”