Open jmsull opened 1 year ago
v and v' look pretty bad - lots of room to improve
Sorry title label on second to last plot is wrong, should say delta'
BTW this is really long mode, $k \sim 0.003$
Now training with 50 iters of Adam with $\eta=1$, followed by 50 with $\eta=0.1$, 20 with $\eta=0.01$, and 10 iters of BFGS (default hyperparameters) - it looks a little better, especially in the solutions, maybe not so much in the reconstructions of $u'$.
Reconstruction:
The loss curve:
It looks like maybe bfgs is starting to just turn down? But the BFGS iters are super expensive (I suppose due to Hessian approximation, even with forward diff, which I assume it is using for that). We should perhaps run this on something with more oomph than my laptop...
Some other observations:
Another thing I'm eager to try is adding more data and batching over k, which will be closer to what we want to do eventually...
Round 1 of very simple Adam opt plots on cdm at fixed background:
delta and v
reconstructed delta', v'