Robust Learning under Uncertain Test Distributions: Relating Covariate Shift to Model Misspecification

By Junfeng Wen, Chun-Nam Yu, R. Greiner. 2014

118 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.

In Optimization & Training

Citations in the corpus

Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth Games: Convergence Analysis under Expected Co-coercivity (2021, background): “Such ﬁnite sum formulations appear in several machine learning applications such as generative adversarial networks (GANs) [Goodfellow et al., 2014], robust learning [Wen et al., 2014] or even some formulations of reinforcement learning [Pfau and Vinyals, 2016].”
Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates (2019, methodology): “These problems encompass both convex minimization and saddle point problems arising in robust supervised learning [8, 88] and learning with non-separable losses or regularizers [35, 4].”
Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization (2019, neutral): “The problem with applying DRO to overparameterized models is that if a model achieves zero training loss, then it is optimal on both the worst-case (DRO) and the average training objectives (Zhang et al., 2017; Wen et al., 2014).”
An introduction to domain adaptation and transfer learning (2018, background): “Examples of exploitable relationships include: the existence of a single good predictor for both domains [17,18,16,26], constrained worst-case labellings [200,135], low-datadivergence [17,18,16], the existence of a domain manifold [83,7,157], conditional independence of class and target given source”
A Review of Domain Adaptation without Target Labels (2019, background): “One can be less sensitive to poor weights by minimizing risk with respect to worst-case weights [15]:”
Domain Aggregation Networks for Multi-Source Domain Adaptation (2019, methodology): “The question is whether one can maintain the O ( k ) complexity given that we need to compute the weights using Eq.”
Stable Prediction across Unknown Environments (2018, methodology): “A variety of techniques have been proposed to estimate the density ratio, including discriminative estimation [2], Kullaback-Leibler importance estimation [3], kernel mean matching [4] [19], maximum entropy methods [5], minimax optimization [20], and robust biasaware approach [6].”
What Clinicians Want: Contextualizing Explainable Machine Learning for Clinical End Use (2019, methodology): “It can lead to an overall underperforming system and can further reduce the effectiveness of some methods used for dealing with model uncertainty (Wen et al., 2014).”
An Empirical Analysis of Backward Compatibility in Machine Learning Systems (2020, background): “r reliability. Prior works on ML reliability and robustness have sought to develop techniques that enable models to perform successfully under the presence of data shifts or adversarial perturbations [6, 22, 27, 40]. However, these studies investigate the reliability of models in isolation, quantifi”
An Investigation of Why Overparameterization Exacerbates Spurious Correlations (2020, methodology): “Our focus is on the overparameterized, zero-training-error regime; here, previous methods based on reweighting and DRO are ineffective (Wen et al., 2014; Byrd & Lipton, 2019; Sagawa et al., 2020).”
Distributionally Robust Neural Networks (2020, background): “, 2017)); any such model would be (near) optimal for both the average and worst-case training losses, so there is little incentive for their minimizers to differ (Wen et al., 2014).”