Related papers: Distributionally Robust Post-hoc Classifiers under…

The performance of machine learning models can significantly degrade under distribution shifts of the data. We propose a new method for classification which can improve robustness to distribution shifts, by combining expert knowledge about…

Machine learning has demonstrated remarkable prediction accuracy over i.i.d data, but the accuracy often drops when tested with data from another distribution. In this paper, we aim to offer another view of this problem in a perspective…

Our goal is to improve reliability of Machine Learning (ML) systems deployed in the wild. ML models perform exceedingly well when test examples are similar to train examples. However, real-world applications are required to perform on any…

Machine learning algorithms with empirical risk minimization are vulnerable under distributional shifts due to the greedy adoption of all the correlations found in training data. There is an emerging literature on tackling this problem by…

An interesting phenomenon arises: Empirical Risk Minimization (ERM) sometimes outperforms methods specifically designed for out-of-distribution tasks. This motivates an investigation into the reasons behind such behavior beyond algorithmic…

The robustness of machine learning algorithms to distributions shift is primarily discussed in the context of supervised learning (SL). As such, there is a lack of insight on the robustness of the representations learned from unsupervised…

We consider the problem of training a classification model with group annotated training data. Recent work has established that, if there is distribution shift across different groups, models trained using the standard empirical risk…

Predictive models that generalize well under distributional shift are often desirable and sometimes crucial to building robust and reliable machine learning applications. We focus on distributional shift that arises in causal inference from…

Spurious correlations that lead models to correct predictions for the wrong reasons pose a critical challenge for robust real-world generalization. Existing research attributes this issue to group imbalance and addresses it by maximizing…

Empirical risk minimization (ERM) is known in practice to be non-robust to distributional shift where the training and the test distributions are different. A suite of approaches, such as importance weighting, and variants of…

In this paper, we present results on improving out-of-domain weather prediction and uncertainty estimation as part of the \texttt{Shifts Challenge on Robustness and Uncertainty under Real-World Distributional Shift} challenge. We find that…

Meta-learning is a practical learning paradigm to transfer skills across tasks from a few examples. Nevertheless, the existence of task distribution shifts tends to weaken meta-learners' generalization capability, particularly when the…

Conformal prediction has emerged as a rigorous means of providing deep learning models with reliable uncertainty estimates and safety guarantees. Yet, its performance is known to degrade under distribution shift and long-tailed class…

We conduct an extensive study on the state of calibration under real-world dataset shift for image classification. Our work provides important insights on the choice of post-hoc and in-training calibration techniques, and yields practical…

With the recent advances in the field of deep learning, learning-based methods are widely being implemented in various robotic systems that help robots understand their environment and make informed decisions to achieve a wide variety of…

Empirical risk minimization often performs poorly when the distribution of the target domain differs from those of source domains. To address such potential distribution shifts, we develop an unsupervised domain adaptation approach that…

It has been shown that instead of learning actual object features, deep networks tend to exploit non-robust (spurious) discriminative features that are shared between training and test sets. Therefore, while they achieve state of the art…

AI applications are becoming increasingly visible to the general public. There is a notable gap between the theoretical assumptions researchers make about computer vision models and the reality those models face when deployed in the real…

Generating calibrated and sharp neural network predictive distributions for regression problems is essential for optimal decision-making in many real-world applications. To address the miscalibration issue of neural networks, various…

Learning with identical train and test distributions has been extensively investigated both practically and theoretically. Much remains to be understood, however, in statistical learning under distribution shifts. This paper focuses on a…