paper-with-me

홈 › Papers

Distribution Density, Tails, and Outliers in Machine Learning: Metrics and Applications

2019-10-29 · Nicholas Carlini, Úlfar Erlingsson, Nicolas Papernot

We develop techniques to quantify the degree to which a given (training or testing) example is an outlier in the underlying distribution. We evaluate five methods to score examples in a dataset by how well-represented the examples are, for different plausible definitions of "well-represented", and apply these to four common datasets: MNIST, Fashion-MNIST, CIFAR-10, and ImageNet. Despite being independent approaches, we find all five are highly correlated, suggesting that the notion of being well-represented can be quantified. Among other uses, we find these methods can be combined to identify (a) prototypical examples (that match human expectations); (b) memorized training examples; and, (c) uncommon submodes of the dataset. Further, we show how we can utilize our metrics to determine an improved ordering for curriculum learning, and impact adversarial robustness. We release all metric values on training and test sets we studied.

📄 PDF Abstract BibTeX arXiv:1910.13427

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial RobustnessBIG-bench Machine Learning

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

A Normal Variance Mixture Model for Robust Kalman Filtering

2025-02-25 · Michael J. Walsh

The Kalman filter is ubiquitous for state space models because of its desirable statistical properties, ease of implementation, and generally good performance. However, it can perform poorly in the presence of outliers, …

State Space Models

Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completion

2021-11-24 · Tong Wu, Liang Pan, Junzhe Zhang, Tai Wang 외

Chamfer Distance (CD) and Earth Mover's Distance (EMD) are two broadly adopted metrics for measuring the similarity between two point sets. However, CD is usually insensitive to mismatched local density, and EMD is usual…

Point Cloud Completion

Balanced Chamfer Distance as a Comprehensive Metric for Point Cloud Completion

2021-12-01 · NeurIPS 2021 12 · Tong Wu, Liang Pan, Junzhe Zhang, Tai Wang 외

Chamfer Distance (CD) and Earth Mover’s Distance (EMD) are two broadly adopted metrics for measuring the similarity between two point sets. However, CD is usually insensitive to mismatched local density, and EMD is usual…

Point Cloud Completion

Asymmetry in Distributions of Accumulated Gains and Losses in Stock Returns

2025-03-31 · Hamed Farahani, R. A. Serota

We study decades-long historic distributions of accumulated S\&P500 returns, from daily returns to those over several weeks. The time series of the returns emphasize major upheavals in the markets -- Black Monday, Tech B…

Reliable Fidelity and Diversity Metrics for Generative Models

2020-02-23 · ICML 2020 1 · Muhammad Ferjad Naeem, Seong Joon Oh, Youngjung Uh, Yunjey Choi 외

Devising indicative evaluation metrics for the image generation task remains an open problem. The most widely used metric for measuring the similarity between real and generated images has been the Fr\'echet Inception Di…

DiversityImage Generation