intrinsic-dimension
None
view repo
Many recently trained neural networks employ large numbers of parameters to achieve good performance. One may intuitively use the number of parameters required as a rough gauge of the difficulty of a problem. But how accurate are such notions? How many parameters are really needed? In this paper we attempt to answer this question by training networks not in their native parameter space, but instead in a smaller, randomly oriented subspace. We slowly increase the dimension of this subspace, note at which dimension solutions first appear, and define this to be the intrinsic dimension of the objective landscape. The approach is simple to implement, computationally tractable, and produces several suggestive conclusions. Many problems have smaller intrinsic dimensions than one might suspect, and the intrinsic dimension for a given dataset varies little across a family of models with vastly different sizes. This latter result has the profound implication that once a parameter space is large enough to solve a problem, extra parameters serve directly to increase the dimensionality of the solution manifold. Intrinsic dimension allows some quantitative comparison of problem difficulty across supervised, reinforcement, and other types of learning where we conclude, for example, that solving the inverted pendulum problem is 100 times easier than classifying digits from MNIST, and playing Atari Pong from pixels is about as hard as classifying CIFAR-10. In addition to providing new cartography of the objective landscapes wandered by parameterized models, the method is a simple technique for constructively obtaining an upper bound on the minimum description length of a solution. A byproduct of this construction is a simple approach for compressing networks, in some cases by more than 100 times.
READ FULL TEXT
Although pretrained language models can be fine-tuned to produce
state-o...
read it
Traditional linear subspace reduced order models (LS-ROMs) are able to
a...
read it
We investigate the difficulties of training sparse neural networks and m...
read it
In this short note we focus on two recently introduced parameters in the...
read it
When analyzing empirical data, we often find that global linear models
o...
read it
Stochastic Gradient Descent (SGD) has proven to be remarkably effective ...
read it
We consider a common measurement paradigm, where an unknown subset of an...
read it
None
Comments
There are no comments yet.