REVIEW 2 cited by
JFB: Jacobian-Free Backpropagation for Implicit Networks
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
A promising trend in deep learning replaces traditional feedforward networks with implicit networks. Unlike traditional networks, implicit networks solve a fixed point equation to compute inferences. Solving for the fixed point varies in complexity, depending on provided data and an error tolerance. Importantly, implicit networks may be trained with fixed memory costs in stark contrast to feedforward networks, whose memory requirements scale linearly with depth. However, there is no free lunch -- backpropagation through implicit networks often requires solving a costly Jacobian-based equation arising from the implicit function theorem. We propose Jacobian-Free Backpropagation (JFB), a fixed-memory approach that circumvents the need to solve Jacobian-based equations. JFB makes implicit networks faster to train and significantly easier to implement, without sacrificing test accuracy. Our experiments show implicit networks trained with JFB are competitive with feedforward networks and prior implicit networks given the same number of parameters.
Forward citations
Cited by 2 Pith papers
-
The Equilibrium Is the Initialization: Lazy Identity Collapse in Physics-Structured Deep Equilibrium Reasoning
In a port-Hamiltonian DEQ with learned initialization, the equilibrium equals the start to numerical precision and contributes +0.00 pp accuracy in 18 of 19 runs; a four-test diagnostic exposes the no-op.
-
NeuroForge: A Self-Correcting, Geometry-Native Neural CFD Engine with Calibrated Physics-Residual Trust
The steady-RANS residual of a neural CFD prediction is a backbone-robust case-level trust signal but a poor correction objective; a supervised DEQ corrector cuts field MSE on a SOTA backbone without needing residual c...
Discussion (0). Sign in to comment.