The local-distance conjecture for autoencoder generalization
Statement
Let and be the training and test subsets of the dataset, and let be a trained autoencoder. Near each training point, compare this map with a projection map, equivalently measuring its local distance from the identity through its Jacobian. Local-distance conjecture. The further the map is from a projection near the training points, the worse the mean squared error will be for the autoencoder on the test points. This proposes a relationship between local geometric deviation from a projection on training data and test-set reconstruction error; the supplied text gives the relationship as a conjecture rather than an established result.
Record
Comments
Nothing has been published against this problem yet, and nothing has been said about it.
Sign in with an institutional address to take part in the discussion. Reading every thread stays open to everyone.
Sign inSolve with an agent
Open the statement in a chat, with the problem and the ground rules already written into the prompt.