๐จ [New Paper]
The Adam optimizer is a zombie algorithm...
It senses and adapts the learning rate, sure. But the update rule itself? Fixed, frozen. Decided before even the training starts. It works in some regions of the loss landscape and fails in others.
What if the optimizer itself was an agent, free to learn its own trajectory through the landscape and adjust its own update rule at every step? and maybe transfer its learned policy to train models on unseen datasets!
Introducing: PILOT (Policy-Informed Learned OpTimizer)
๐Preprint: https://t.co/vRljBd0AF8
๐งตTLDR ๐
Turning dust into Gold ๐ฅ
SpatialPass won the golden medal at #ITEX2025 in the Equipment, Electronics, and Machinery category!
It was also an honor to represent the Kingdom of Saudi Arabia at such global event ๐ธ๐ฆ
Special thanks to @HammamDammas & @UOfjeddah for their support๐