Comment by erichocean
22 days ago
> PC-ALM closes the PC-BP gap at matched inference budget in nonlinear networks
Okay, so no efficiency improvement?
22 days ago
> PC-ALM closes the PC-BP gap at matched inference budget in nonlinear networks
Okay, so no efficiency improvement?
Backprop has significant costs, if a local solution truly matches its performance, it will be dropped like a hot potato.
Agreed, but how will we find out? Pre-training alone on frontier-class models costs billions of dollars.