数据粗粒化可以提高模型性能
Alex Nguyen1, David J Schwab2, Vudtiwat Ngampruetikorn3
1Princeton Neuroscience Institute, Princeton University, Princeton, NJ 08540, USA.
ArXiv
|September 26, 2025
概括
丢失的数据转换可以令人惊地提高机器学习概括. 一个高通数据粗粒度方案,删除不太相关的特征,通过隔离预测信号来提高模型性能.
科学领域:
- 机器学习 机器学习
- 统计物理 统计物理
- 数据科学数据科学数据科学
背景情况:
- 丢失的数据转换通常会丢弃信息.
- 像数据修剪和丢失数据增强这样的技术可以悖论地改善机器学习概括.
- 了解这种现象背后的机制对于开发更有效的ML模型至关重要.
研究的目的:
- 调查信息丢失的悖论,提高机器学习中的概括性.
- 使用可解决的模型分析数据粗粒度对预测风险的影响.
- 为某些数据增强策略的好处提供分析解释.
主要方法:
- 在数据粗粒度下研究了高维,度规则化的线性回归.
- 受重新规范化集团启发的雇佣计划,系统地根据相关性抛弃特征.
- 分析了预测风险对粗粒度程度的依赖性.
主要成果:
- 发现了数据粗粒度和预测风险之间的非单调关系.
- 一个高通粗粒度方案,过出低信号特征,改进了泛化.
- 一个低通路方案,整合出高信号特征,被证明是有害的.
- 证明这种非单调性是数据粗粒度的明显效应,而不是双重血统的工件.
结论:
- 仔细的数据增强,通过剥离不相关的自由度,可以隔离更多的预测信号并增强模型概括性.
- 该研究突出了由数据结构影响的复杂,非单调的风险景观.
- 统计物理原理为理解现代机器学习现象提供了有价值的框架.
相关概念视频
Types of Aggregate Grading
1.4K
Aggregate grading is crucial in economically obtaining a concrete mix with adequate strength, reasonable workability, and minimal segregation. There are four types of aggregate gradation: well-graded, uniformly (or one-sized) graded, gap-graded, and open-graded.
Well-graded aggregates include a complete range of necessary size fractions that fit together to create a dense matrix with minimal voids, represented by a smooth, continuous gradation curve. This type of grading ensures good...
Well-graded aggregates include a complete range of necessary size fractions that fit together to create a dense matrix with minimal voids, represented by a smooth, continuous gradation curve. This type of grading ensures good...
1.4K
Design Example: Aggregate Gradation
311
The right type and quality of aggregates are crucial for concrete as they significantly influence its properties, mix proportions, and cost-effectiveness. If different sources are available for sand, the commonly used fine aggregate in concrete, the selection of sand is primarily based on its gradation.
The grading, or particle-size distribution, of sand is determined using sieve analysis, with standard sizes ranging from 150 μm to 10 mm (ASTM No. 100 sieve to 3⁄8 in. sieve). Sand is...
The grading, or particle-size distribution, of sand is determined using sieve analysis, with standard sizes ranging from 150 μm to 10 mm (ASTM No. 100 sieve to 3⁄8 in. sieve). Sand is...
311
Quantifying and Rejecting Outliers: The Grubbs Test
3.5K
Sometimes, a data set can have a recorded numerical observation that greatly deviates from the rest of the data. Assuming that the data is normally distributed, a statistical method called the Grubbs test can be used to determine whether the observation is truly an outlier. To perform a two-tailed Grubbs test, first, calculate the absolute difference between the outlier and the mean. Then, calculate the ratio between this difference and the standard deviation of the sample. This...
3.5K
Sieve Analysis and Grading Curves
921
Sieve analysis is a method used to determine the particle size distribution of aggregate materials. This process involves the following steps:
921
Expected Frequencies in Goodness-of-Fit Tests
7.2K
A goodness-of-fit test is conducted to determine whether the observed frequency values are statistically similar to the frequencies expected for the dataset. Suppose the expected frequencies for a dataset are equal such as when predicting the frequency of any number appearing when casting a die. In that case, the expected frequency is the ratio of the total number of observations (n) to the number of categories (k).
7.2K
Improving Translational Accuracy
14.1K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
14.1K

