GitLab

Technical

• Training on large spaces (aka out-of-core or online learning) to avoid the following:
  ValueError: Cannot create a tensor proto whose content is larger than 2GB.
• Generate train/test splits for all spaces
• Make a AdanetWrapper class
• Serialize generated models (aka Save and Load functions)
• Standard predictor interface (aka Fit and Predict functions)

Validation

• Plot train-test performance vs. epoch (Tensorboard?)
• Scatterplot test y_pred vs y_true for each component, annotate correlation
• Previous two comparing to simple sklearn.linear_model.LinearRegression
• Are distances conserved? y_true pairwise distance vs. y_pred pairwise distance (cosine)

Gridsearch

Training on a small A5 subset reveals that we can overfit, we must be able to overfit also on large space, so

• Gridsearch on 3 parameters:

• learning_rate

• adanet lambda

• layer_size

• additional gridsearch as discussed in comments

• learning_rate: [1e-2, 1e-3]

• train_step: [1e5, 1e6]

• layer_size: [2**9, 2**8, 2**7]