Re:The boundary of neural network trainability is fractal
by catlifeonmars on Monday February 19, 2024 @02:11PM
(#39433471)
So what exactly are we looking at here? Did the authors only use two hyperparameters for the purpose of this visualization?
[ Parent
| on HN ]
Re:The boundary of neural network trainability is fractal
by yazzku on Monday February 19, 2024 @03:59PM
(#39434740)
It's explained in the post:
> Have you ever done a dense grid search over neural network hyperparameters? Like a really dense grid search? It looks like this (!!). Blueish colors correspond to hyperparameters for which training converges, redish colors to hyperparameters for which training diverges.
Re:The boundary of neural network trainability is fractal
by catlifeonmars on Monday February 19, 2024 @07:37PM
(#39436636)
I saw this, but am still not clear on what the axes represent. I assume two hyperparameters, or possibly two orthogonal principal components. I guess my point is it’s not clear how/which parameters are mapped onto the image.
Re:The boundary of neural network trainability is fractal
by bosco_mcnasty on Tuesday February 20, 2024 @06:09PM
(#39448185)
your point is valid but the paper explains it clearly and obviously. they are NOT dimensionally reduced hyperparameters, no. The hyperparameters are learning rates, that's it. X axis, learning rate for input (1 hidden layer). Y axis, learning rate for output layer.
So what this is saying, for certain ill-chosen learning weights, model convergence is for lack of a better word, chaotic and unstable.
Re:The boundary of neural network trainability is fractal
by ks1723 on Tuesday February 20, 2024 @06:32PM
(#39448386)
Just to add to this, only the two learning rates are changed, everything else including initialization and data is fixed. From the paper:
Training consists of 500 (sometimes 1000) iterations of full batch steepest gradient descent. Training is performed for a 2d grid of η0 and η1 hyperparameter values, with all other hyperparameters held fixed (including network initialization and training data).