Stop Using The Same Image in Bias-Variance Trade-off Explanation

This will be a short 1-minute post of my thoughts about we shouldn’t use the following image while explaining or learning bias-variance tradeoff

Recently, while reading lectures at Middlesex University Dubai, I was asked a question regarding Bias-Variance Trade-off. One of the students didn’t quite understand, how to get from pictureA to pictureB:

All-over-the-internet explanation of bias-variance tradeoff

He was trying to understand the concept by reading some tutorials and videos. He saw the 4-aim image in almost every post, but he was confused. Not only he had found it difficult to understand how 4 scenarios in pictureA turn into 3 scenarios in pictureB, but he also hasn’t found any example of High Bias — High Variance models. To be honest it took me some time to think of such an example (want to hear your thoughts in the comments, so not to spoil my ideas) in order to explain the concept in practical cases.

I honestly believe it’s time to stop using the 4-target picture. If you feel, that the aims are the best way to explain bias and variance, consider using the following Venn diagram on the left.

As you might notice, with this approach, it becomes much easier to map low variance-bias explanations with underfit-sweet-overfit plots:

How I suggest the explanation of bias-variance tradeoff should be illustrated

I’m not a designer, so there are plenty more improvements, that can be made. But from the conceptual point of view, I think this was of illustrating the idea of bias-variance tradeoff is more straightforward. Most importantly, it gave a clearer picture to the student about the BVT topic.