paper-with-me

홈 › Papers

Simple data balancing achieves competitive worst-group-accuracy

2021-10-27 · Badr Youbi Idrissi, Martin Arjovsky, Mohammad Pezeshki, David Lopez-Paz

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.

📄 PDF Abstract BibTeX arXiv:2110.14503

Code (1)

facebookresearch/balancinggroups 공식 구현 pytorch

Tasks

Model SelectionOut-of-Distribution Generalization

Similar Papers 제목 키워드 기반

Outcome Assumptions and Duality Theory for Balancing Weights

2022-03-17 · David Bruns-Smith, Avi Feller

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

2026-06-15 · Sungbum Kim, Jiayi Wang arxiv

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 Inference

The SMART approach to instance-optimal online learning

2024-02-27 · Siddhartha Banerjee, Alankrita Bhatt, Christina Lee Yu

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

2021-10-12 · Paul Michel, Sebastian Ruder, Dani Yogatama

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 Modelling

Covariate Balancing Methods for Randomized Controlled Trials Are Not Adversarially Robust

2021-10-25 · Hossein Babaei, Sina AlEMohammad, Richard Baraniuk

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