paper-with-me

Papers

Importance Tempering: Group Robustness for Overparameterized Models

2022-09-19 · Yiping Lu, Wenlong Ji, Zachary Izzo, Lexing Ying

Although overparameterized models have shown their success on many machine learning tasks, the accuracy could drop on the testing distribution that is different from the training one. This accuracy drop still limits applying machine learning in the wild. At the same time, importance weighting, a traditional technique to handle distribution shifts, has been demonstrated to have less or even no effect on overparameterized models both empirically and theoretically. In this paper, we propose importance tempering to improve the decision boundary and achieve consistently better results for overparameterized models. Theoretically, we justify that the selection of group temperature can be different under label shift and spurious correlation setting. At the same time, we also prove that properly selected temperatures can extricate the minority collapse for imbalanced classification. Empirically, we achieve state-of-the-art results on worst group classification tasks using importance tempering.

📄 PDF Abstract BibTeX arXiv:2209.08745

Code (0)

등록된 구현이 없습니다.

Tasks

imbalanced classification

Similar Papers 제목 키워드 기반

Sharp analysis of out-of-distribution error for "importance-weighted" estimators in the overparameterized regime

2024-05-10 · Kuo-Wei Lai, Vidya Muthukumar

Overparameterized models that achieve zero training error are observed to generalize well on average, but degrade in performance when faced with data that is under-represented in the training sample. In this work, we stu…

Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization

2019-11-20 · Shiori Sagawa, Pang Wei Koh, Tatsunori B. Hashimoto, Percy Liang

Overparameterized neural networks can be highly accurate on average on an i.i.d. test set yet consistently fail on atypical groups of the data (e.g., by learning spurious correlations that hold on average but not in such…

Domain GeneralizationNatural Language InferenceOut-of-Distribution GeneralizationStochastic Optimization

DISTRIBUTIONALLY ROBUST NEURAL NETWORKS FOR GROUP SHIFTS ON THE IMPORTANCE OF REGULARIZATION FOR WORST-CASE GENERALIZATION

2022-01-17 · ICLR Track Blog 2022 5 · Anonymous

Overparameterized neural networks can be highly accurate on average on an i.i.d. test set yet consistently fail on atypical groups of the data (e.g., by learning spurious correlations that hold on average but not in such…

Natural Language InferenceStochastic Optimization

FlowVAT: Normalizing Flow Variational Inference with Affine-Invariant Tempering

2025-05-15 · Juehang Qin, Shixiao Liang, Christopher Tunnell

Multi-modal and high-dimensional posteriors present significant challenges for variational inference, causing mode-seeking behavior and collapse despite the theoretical expressiveness of normalizing flows. Traditional an…

Variational Inference

Scalable Importance Tempering and Bayesian Variable Selection

2018-05-01 · Giacomo Zanella, Gareth Roberts

We propose a Monte Carlo algorithm to sample from high dimensional probability distributions that combines Markov chain Monte Carlo and importance sampling. We provide a careful theoretical analysis, including guarantees…

Variable Selection