glen/dyna3
1
0
Fork 0
Code Issues 11 Pull Requests 1 Actions Projects Releases 2 Wiki Activity

Correct improvement threshold by using unit step

Browse Source 
Our formula for the improvement theshold works when the step size is
an absolute distance. However, in commit `4d5ea06`, the step size was
measured relative to the current gradient instead. This commit scales
the base step to unit length, so now the step size really is an absolute
distance.
This commit is contained in:
Aaron Fenyes 2024-07-10 23:31:44 -07:00
parent 4d5ea062a3
commit d538cbf716
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
engine-proto/gram-test/Engine.jl
View File

@ -120,6 +120,7 @@ function realize_gram(
# find negative gradient of loss function
neg_grad = 4*Q*L*Δ_proj
slope = norm(neg_grad)
dir = neg_grad / slope
# store current position, loss, and slope
L_last = L
@ -135,7 +136,7 @@ function realize_gram(
empty!(history.last_line_loss)
for backoff_steps in 0:max_backoff_steps
history.stepsize[end] = stepsize
L = L_last + stepsize * neg_grad
L = L_last + stepsize * dir
Δ_proj = proj_diff(gram, L'*Q*L)
loss = dot(Δ_proj, Δ_proj)
improvement = loss_last - loss