paper-with-me

Papers

Robust Generalization despite Distribution Shift via Minimum Discriminating Information

2021-06-08 · NeurIPS 2021 12 · Tobias Sutter, Andreas Krause, Daniel Kuhn

Training models that perform well under distribution shifts is a central challenge in machine learning. In this paper, we introduce a modeling framework where, in addition to training data, we have partial structural knowledge of the shifted test distribution. We employ the principle of minimum discriminating information to embed the available prior knowledge, and use distributionally robust optimization to account for uncertainty due to the limited samples. By leveraging large deviation results, we obtain explicit generalization bounds with respect to the unknown shifted distribution. Lastly, we demonstrate the versatility of our framework by demonstrating it on two rather distinct applications: (1) training classifiers on systematically biased data and (2) off-policy evaluation in Markov Decision Processes.

📄 PDF Abstract BibTeX arXiv:2106.04443

Code (2)

pmdidro/PMDI_DRO 공식 구현
tobsutter/pmdi_dro 공식 구현

Tasks

Generalization BoundsOff-policy evaluation

Similar Papers 제목 키워드 기반

Memory Classifiers: Two-stage Classification for Robustness in Machine Learning

2022-06-10 · Souradeep Dutta, Yahan Yang, Elena Bernardis, Edgar Dobriban 외

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 exp…

BIG-bench Machine LearningClassificationData AugmentationGeneralization Bounds+1

Generalization of Scaled Deep ResNets in the Mean-Field Regime

2024-03-14 · Yihang Chen, Fanghui Liu, Yiping Lu, Grigorios G. Chrysos 외

Despite the widespread empirical success of ResNet, the generalization properties of deep ResNet are rarely explored beyond the lazy training regime. In this work, we investigate \emph{scaled} ResNet in the limit of infi…

Generalization Bounds

Trained Transformers Learn Linear Models In-Context

2023-06-16 · Ruiqi Zhang, Spencer Frei, Peter L. Bartlett

Attention-based neural networks such as transformers have demonstrated a remarkable ability to exhibit in-context learning (ICL): Given a short prompt sequence of tokens from an unseen task, they can formulate relevant p…

In-Context Learningregression

Towards In-distribution Compatibility in Out-of-distribution Detection

2022-08-29 · Boxi Wu, Jie Jiang, Haidong Ren, Zifan Du 외

Deep neural network, despite its remarkable capability of discriminating targeted in-distribution samples, shows poor performance on detecting anomalous out-of-distribution data. To address this defect, state-of-the-art …

Out-of-Distribution Detection

Domain-wise Adversarial Training for Out-of-Distribution Generalization

2021-09-29 · Shiji Xin, Yifei Wang, Jingtong Su, Yisen Wang

Despite the impressive success on many tasks, deep learning models are shown to rely on spurious features, which will catastrophically fail when generalized to out-of-distribution (OOD) data. To alleviate this issue, Inv…

DiversityOut-of-Distribution Generalization