Simple data balancing achieves competitive worst-group-accuracy
We study the problem of learning classifiers that perform well across (known or unknown) groups of data. After observing that common worst-group-accuracy datasets suffer from substantial imbalances, we set out to compare state-of-the-art methods to simple balancing of classes and groups by either subsampling or reweighting data. Our results show that these data balancing baselines achieve state-of-the-art-accuracy, while being faster to train and requiring no additional hyper-parameters. In addition, we highlight that access to group information is most critical for model selection purposes, and not so much during training. All in all, our findings beg closer examination of benchmarks and methods for research in worst-group-accuracy optimization.
Code (1)
Tasks
Model SelectionOut-of-Distribution GeneralizationSimilar Papers 제목 키워드 기반
Outcome Assumptions and Duality Theory for Balancing Weights
We study balancing weight estimators, which reweight outcomes from a source population to estimate missing outcomes in a target population. These estimators minimize the worst-case error by making an assumption about the…
Kernel-Based Functional Balancing for Causal Inference with Compositional Treatments
We study causal effect estimation with compositional treatments, where the exposure lies on a simplex and the estimand is defined over compositions rather than scalar or binary values. By considering a projection of the …
Causal InferenceThe SMART approach to instance-optimal online learning
We devise an online learning algorithm -- titled Switching via Monotone Adapted Regret Traces (SMART) -- that adapts to the data and achieves regret that is instance optimal, i.e., simultaneously competitive on every inp…
Balancing Average and Worst-case Accuracy in Multitask Learning
When training and evaluating machine learning models on a large number of tasks, it is important to not only look at average task accuracy -- which may be biased by easy or redundant tasks -- but also worst-case accuracy…
image-classificationImage ClassificationLanguage ModelingLanguage ModellingCovariate Balancing Methods for Randomized Controlled Trials Are Not Adversarially Robust
The first step towards investigating the effectiveness of a treatment via a randomized trial is to split the population into control and treatment groups then compare the average response of the treatment group receiving…
Adversarial Attack