0
Computing Effective Dimension for Quantum ML Models in PyTorch
https://towardsdatascience.com/computing-effective-dimension-for-quantum-ml-models-in-pytorch/(towardsdatascience.com)Effective dimension quantifies a model's true learning capacity by measuring how many parameter directions are distinguishable by data, moving beyond simple parameter counts. Its calculation involves approximating the Fisher Information Matrix using data samples and solving a complex integral over the parameter space via Monte Carlo sampling. This sampling can be performed globally across all parameters or locally within a small region, though naive local sampling can lead to incorrect density clustering and must be carefully implemented.
0 points•by will22•3 hours ago
Comments (0)
No comments yet. Be the first to comment!
Have an account? Log in to join the discussion.