Research article · Results

Results: where does backprop clearly win?

Kāula research note, November 2, 2026. Results for the pre-registered gate in Where does backprop clearly win?. Every number below comes from the pre-registered analysis script and its raw results.

Verdict

No architecture qualifies. On none of the four networks does backprop beat the better of feedback alignment and sign-symmetry by 10 points. The largest gap is 5.3 points, on the 3-layer convnet.

As pre-registered, there is no headroom at this budget, so rule discovery waits for deeper networks and longer training on rented GPUs.

1. Results

CIFAR-10 test accuracy, mean of 2 seeds, after 4 epochs on 25,000 training images.

NetworkBackpropFeedback alignmentSign-symmetryGap (backprop − best alternative)
MLP, 3 hidden layers48.9%25.7%48.7%0.2 points
Convnet, 3 layers54.7%49.4%46.7%5.3 points
Convnet, 5 layers65.8%55.0%64.6%1.2 points
Convnet, 7 layers69.0%48.9%66.5%2.5 points

2. What the numbers say

The verdict turns on sign-symmetry. Feedback alignment does fall well behind backprop: by 23 points on the MLP, 11 on the 5-layer convnet and 20 on the 7-layer convnet. But the rule compares backprop with the better alternative, and sign-symmetry stays within 2.5 points of backprop everywhere except the 3-layer convnet.

The following observations weren't part of the pre-registered rule, so they are exploratory:

3. Deviations from the plan

4. Limitations

What's next

The rule-discovery search needs a testbed where every known alternative to backprop clearly loses. That means deeper networks and longer schedules than fit on one laptop overnight. That step moves to rented GPUs.

All notes · The four pre-registrations