Hacker News Reader

Comment by ipsum2 | Hacker News Reader

From the paper:

> This paper is the first to provide compelling evidence that wellregularized neural networks (even simple MLPs!) indeed surpass the current state-of-the-art models in tabular datasets, including recent neural network architectures and GBDT (Section 6).

> Next, we analyze the empirical significance of our well-regularized MLPs against the GBDT implementations in Figure 2b. The results show that our MLPs outperform both GBDT variants (XGBoost and auto-sklearn) with a statistically significant margin.

They test against XGBoost, GBDT Auto-sklearn, and others. Did you read the paper?

View on HN

> They test against XGBoost, GBDT Auto-sklearn, and others. Did you read the paper?

Yes. Did you read my comment?

They compare NN + Cocktail vs. vanilla XGB. They don't compare NN + Cocktail vs. XGB + Cocktail.

To make it crystal clear, if I wrote a paper "existing medicine A enhanced with novel method B is more effective than existing medicine C" and I did not include the control "C + B" (assuming if relevant, which is the case here), that'd be bad science. It's very much possible that novel method B is doing the heavy lifting and A isn't all that relevant. s/A/NN, s/B/Cocktail, s/C/XGBoost.

How would you even apply layer normalization or SWA to XGB? These methods are neural net specific.

GBDT have their own set of hyperparameters such as learning rate, number of trees, min samples per bin, l0, l1, etc. So you could definitely also create an appropriate cocktail to optimize on, although GBDT are typically more robust wrt huperparameters.

The authors do claim to do a hyperparameter sweep but only for vanilla XGB hyperparams.

The old "my method (with as much optimization as I could get away with) beats the other method (with as little optimization as I could get away with)"

Yup. The Least Publishable Unit strikes again.

Batch normalization is nothing neural network specific to it if you use it on the input layer. I don't think it matters for a tree algorithm like XGBoost either way though.

SWA is pretty NN specific. So leave it out for XGB. There's a bunch that are relevant, and they could be very important.

Batch norm has an advantage for iterative methods on mini-batches, while XGB uses the full training set. Using batch norm on the full training set is equivalent to Z-normalizing the features, which has no effect at all for XGB as the scale of features plays no role at the split decisions of the tree nodes. Apart few non-parametric data augmentation methods (notice adversarial augmentation is also nn specific), I do not think any other regularization used in that paper can be directly/intuitively applied to XGB.

I don't think every single regularization method in the cocktail can be applied to non-neural-network methods, but I'm pretty sure some of them can, like data augmentation. The authors could have figured out which methods can be applied to non-NN models or considered if equivalent/analogous methods exist. I agree it would make a fairer comparison.

I agree with your point, e.g. data augmentation can be added, but thats pretty much it. All the other regularization techniques they use are neural network specific and cannot be applied to gradient-boosted trees. What I find particularly striking at this paper is that their method trains a single neural network which outperforms an ensemble of decision trees (XGBoost). Asking for perfect apple-to-apple comparisons means also comparing an ensemble of the MLPs vs. XGBoost. In this context, at least the message here is that XGBoost and/or other gradient-boosted methods are not anymore a silver bullet for tabular datasets. Boosting for trees was great in reducing both bias and variance, but apparently neural networks can achieve the same effect with a high capacity (low bias) and a mix of modern regularization techniques (low variance).

Reply on news.ycombinator.com