Why squared error? | benkuhn.net
its computational convenience • connections to the Gaussian distribution • differentiability and basis independence • why not squared error • absolute-error methods
Someone recently asked on the statistics Stack Exchange why the squared error is used in statistics . This is something I'd been wondering about myself recently, so I decided to take a crack at answering it. The post below is adapted from that answer . Why squared error? It's true that one could choose to use, say, the absolute error instead of the squared error. In fact, the absolute error is often closer to what you "care about" when making predictions from your model. For instance, if you buy a stock expecting its future price to be $P_{predicted}$ and its future price is $P_{actual}$ inste
related reading
- How much do you believe your results? — LessWronglesswrong.com
- Nonparametric statistics - Wikipediaen.wikipedia.org
- Not Quite the James-Stein Estimator – econometrics.blogeconometrics.blog
- X explains Z% of the variance in Y — LessWronglesswrong.com
- Huber lossen.wikipedia.org
- Variance of the Estimator in Machine Learningsuzyahyah.github.io
- generalized surearxiv.org
- Standard Error of the Regression vs. R-squared - Statistics By Jimstatisticsbyjim.com
- empirical_bayes_without_prior_or_supervision_raphan.pdfcns.nyu.edu
- Learning to be Bayesian without Supervisionpapers.nips.cc
- Reasoning about Neural Network Training with Bias-Variance Tradeoffbrucewlee.com
- Linear Regressionmlu-explain.github.io