Robust Supervised Learning

By J. Bagnell. 2005

54 citations recorded by the source corpus.

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

Invariant Risk Minimization (2019, background): “Second, we could minimize R(f) = maxe∈Etr R (f) − re, a robust learning objective where the constants re serve as environment baselines [2, 6, 15, 46].”
Conditional variance penalties and domain shift robustness (2017, background): “Causal models thus have the defining advantage that the predictions will be valid even under arbitrarily large interventions on all predictor variables (Haavelmo 1944; Aldrich 1989; Pearl 2009; Schölkopf et al. 2012; Peters et al. 2016; Zhang et al. 2013, 2015; Yu et al. 2017; Rojas-Carulla et al. 2”
Generative Multi-Adversarial Networks (2016, background): “The GAN framework is one of the more recent successes in a line of research on adversarial training in machine learning (Schmidhuber (1992); Bagnell (2005); Ajakan et al. (2014)) where games between learners are carefully crafted so that Nash equilibria coincide with some set of desired optimality c”
Domain-Adversarial Neural Networks (2014, background): “There has been work on learning linear classiﬁers that are robust to changes in the input distribution, based on a minimax formulation (Bagnell, 2005; Liu & Ziebart, 2014).”
Does Distributionally Robust Supervised Learning Give Robust Classifiers? (2016, background): “DRSL with f -divergences: Let q ≪ p denote that q is absolutely continuous w.r.t. p , i.e., p ( x; y ) = 0 implies q ( x; y ) = 0 : Bagnell (2005) and Ben-Tal et al. (2013) considered the particular uncertainty set where and f ( (cid:1) ) is convex with f (1) = 0 .”
An Invitation to Imitation (2015, unknown): “[Bagnell, 2005 ].”
The Risks of Invariant Risk Minimization (2020, background): “Note, however, that we are not hoping to minimize this risk in expectation over the environments; this is already accomplished via ERM or distributionally robust optimization (DRO; Bagnell 2005; Ben-Tal et al. 2009).”
Out-of-Distribution Generalization via Risk Extrapolation (REx) (2020, background): “P e ( x ) varying within a KL-divergence (cid:15) -ball of the empirical distribution (Bagnell, 2005)).”
An Online Learning Approach to Interpolation and Extrapolation in Domain Generalization (2021, methodology): “, 2018); another approach is Distributionally Robust Optimization (DRO), where the test distribution is assumed to lie in some uncertainty set around the training distribution (Bagnell, 2005; Rahimian & Mehrotra, 2019).”