pith. sign in

The same CG solver is reused for both forward and adjoint solves, requiringO(N)total memory

A Implicit Differentiation Givenψ ∗ =A −1bwhereA=L W + Λand downstream lossL: ∂L ∂b =A −1 ∂L ∂ψ ∗ =v,(24) ∂L ∂wij =−v i(ψ∗ i −ψ ∗ j )−v j(ψ∗ j −ψ ∗ i ),(25) wherev=A −1(∂L/∂ψ ∗)is the adjoint variable · 1999

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
browse 1 citing papers

fields

cs.AI 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Metriplector: From Field Theory to Neural Architecture

cs.AI · 2026-03-31 · unverdicted · novelty 6.0

Metriplector treats neural computation as coupled metriplectic field dynamics whose stress-energy tensor readout achieves competitive results on vision, control, Sudoku, language modeling, and pathfinding with small parameter counts.

citing papers explorer

Showing 1 of 1 citing paper.

  • Metriplector: From Field Theory to Neural Architecture cs.AI · 2026-03-31 · unverdicted · none · ref 18

    Metriplector treats neural computation as coupled metriplectic field dynamics whose stress-energy tensor readout achieves competitive results on vision, control, Sudoku, language modeling, and pathfinding with small parameter counts.