paper-with-me

홈 › Papers

Beyond Discrepancy: A Closer Look at the Theory of Distribution Shift

2024-05-29 · Robi Bhattacharjee, Nick Rittler, Kamalika Chaudhuri

Many machine learning models appear to deploy effortlessly under distribution shift, and perform well on a target distribution that is considerably different from the training distribution. Yet, learning theory of distribution shift bounds performance on the target distribution as a function of the discrepancy between the source and target, rarely guaranteeing high target accuracy. Motivated by this gap, this work takes a closer look at the theory of distribution shift for a classifier from a source to a target distribution. Instead of relying on the discrepancy, we adopt an Invariant-Risk-Minimization (IRM)-like assumption connecting the distributions, and characterize conditions under which data from a source distribution is sufficient for accurate classification of the target. When these conditions are not met, we show when only unlabeled data from the target is sufficient, and when labeled target data is needed. In all cases, we provide rigorous theoretical guarantees in the large sample regime.

📄 PDF Abstract BibTeX arXiv:2405.19156

Code (0)

등록된 구현이 없습니다.

Tasks

Learning Theory

Similar Papers 제목 키워드 기반

A Closer Look at the Learnability of Out-of-Distribution (OOD) Detection

2025-01-15 · Konstantin Garov, Kamalika Chaudhuri

Machine learning algorithms often encounter different or "out-of-distribution" (OOD) data at deployment time, and OOD detection is frequently employed to detect these examples. While it works reasonably well in practice,…

Learning TheoryOut of Distribution (OOD) DetectionPAC learning

Beyond AUROC & co. for evaluating out-of-distribution detection performance

2023-06-26 · Galadrielle Humblot-Renaux, Sergio Escalera, Thomas B. Moeslund

While there has been a growing research interest in developing out-of-distribution (OOD) detection methods, there has been comparably little discussion around how these methods should be evaluated. Given their relevance …

Binary ClassificationOut-of-Distribution DetectionOut of Distribution (OOD) Detection

One-Shot Decision-Making with and without Surrogates

2019-12-19 · Jakob Bossek, Pascal Kerschke, Aneta Neumann, Frank Neumann 외

One-shot decision making is required in situations in which we can evaluate a fixed number of solution candidates but do not have any possibility for further, adaptive sampling. Such settings are frequently encountered i…

Decision Makingregression

Cycle Consistent Probability Divergences Across Different Spaces

2021-11-22 · Zhengxin Zhang, Youssef Mroueh, Ziv Goldfeld, Bharath K. Sriperumbudur

Discrepancy measures between probability distributions are at the core of statistical inference and machine learning. In many applications, distributions of interest are supported on different spaces, and yet a meaningfu…

Computational EfficiencyGenerative Adversarial Network

H-divergence: A Decision-Theoretic Discrepancy Measure for Two Sample Tests

2021-01-01 · Shengjia Zhao, Abhishek Sinha, Yutong He, Aidan Perreault 외

Measuring the discrepancy between two probability distributions is a fundamental problem in machine learning and statistics. Based on ideas from decision theory, we investigate a new class of discrepancies that are based…

Vocal Bursts Valence Prediction