I'm not surprised by #1 or #8, but I'm pleasantly surprised by the fact that Leo Breimans paper on Random Forest is still so high up there.
The algorithm is great in its simplicity and it's mind if mind-blowing how a collective of mostly poor predictors can be used to create an ensemble that is generally predictive. It's also so much less data intensive and energy intensive to train than a deep learning algorithm.
Cross validation is a way of calculating the likely uncertainty of any model (it doesn't have to be a machine learning model).
A common cross validation approach is LOOCV (leave one out cross validation), for small datasets. Another is K-folds cross validation. In any case, the basics is to leave out "some amount" of your training data, totally removed from the training process, then you train your model, then you validate it on the trained model. You then repeat this process over the k-folds or each unit of your training data to create a valid uncertainty.
So a few things. First, this a standard approach in machine learning, because once you get stop making the assumptions of frequentism (and you probably should), you no longer get things like uncertainty for free, because the assumptions aren't met.
In some approaches in machine learning, this is necessary because there really isn't a tractable way to get uncertainty from the model (although in others, like random forest, you get cross validation for free).
Cross validation is great because you really don't need to understand anything about the model itself; you just implement the validation strategy and you get a valid answer for the model uncertainty.
We've got a massive stack of evidence showing that progressive policies and candidates are popular and win elections; that centrists and moderates lose elections; and that the main reason why Democrats fail to perform is when they try to get RW'ing voters instead of activating their base, trying to get LW'ing voters. We've got like 2.5 decades of consistent data showing this. The two problems we have are 1) we have a media and Democratic consultant class for whom maintaining control of the party is a higher priority than maintaining control of government as a party, and that 2) these people and the voters have very different interests that don't align and are basically exclusive to one another.
The biggest opposition to Democrats winning elections isn't Republicans, it's Democrats who are wrong about where the country is at, who are wrong about how elections work, and who can't be removed from any office because at its core, the Democratic Party is a fundamentally undemocratic institution (like, we've had supreme court rulings on the matter).
So stack it up. The evidence is clear that Democratic socialist policies win Democrats elections. But with apologists always willing to come out and make apologies for business as usual, well never be able to to break the blood brain barrier within the DNC.
The establishment politicians of the Democratic party are why they are polling at historic lows, but I'm also concerned that too much has been placed on Mamdani's shoulders in regards to the future of the party. Its one race, in a state with a Democratic party that is very different than Democratic parties in the rest of the country, with a voting system that while better, is more subject to uncertainty than we're used to. A lot of fuckery can happen between now and then.
Mamdani isn't a super hero and a lot can happen between here and there. Its a good thing that he's doing well, but its not clear whatsoever that there is a political path towards defeating fascism in the US, even if Mamdani pulls this out. If they do, its a largely aesthetic win; its not like a senate seat or the house is in play from this.
We need to fully digest the fact that politics have failed us and recognize that we may need to move on with regards to the fight against fascism. Ideally, there is both a political path to fighting fascism and a boots on the ground path, but I'm concerned about over investing in political paths which have repeatedly demonstrated themselves to be a waste of resources, effort, and mind share.
