Desynchronous Learning in a Physics-Driven Learning Network

January 10, 2022 Β· Declared Dead Β· πŸ› Journal of Chemical Physics

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Jacob F Wycoff, Sam Dillavou, Menachem Stern, Andrea J Liu, Douglas J Durian arXiv ID 2201.04626 Category cond-mat.soft Cross-listed cs.LG, cs.NE Citations 25 Venue Journal of Chemical Physics Last Checked 3 months ago
Abstract
In a neuron network, synapses update individually using local information, allowing for entirely decentralized learning. In contrast, elements in an artificial neural network (ANN) are typically updated simultaneously using a central processor. Here we investigate the feasibility and effect of desynchronous learning in a recently introduced decentralized, physics-driven learning network. We show that desynchronizing the learning process does not degrade performance for a variety of tasks in an idealized simulation. In experiment, desynchronization actually improves performance by allowing the system to better explore the discretized state space of solutions. We draw an analogy between desynchronization and mini-batching in stochastic gradient descent, and show that they have similar effects on the learning process. Desynchronizing the learning process establishes physics-driven learning networks as truly fully distributed learning machines, promoting better performance and scalability in deployment.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” cond-mat.soft

Died the same way β€” πŸ‘» Ghosted