claim
active
claim:importance-minimality-works-with-p-1-since-splitting-a-causally-important-subcomponent-would-still-raise-the-loss

Importance-minimality works with p>1 since splitting a causally important subcomponent would still raise the loss

Contrast with SDL.

Source paper

extracted_from
Stochastic Parameter Decomposition
(2025) · Lucius Bushnaq · Dan Braun · Lee Sharkey

Neighborhood — ranked by edge-count

Papers (1)

paper

Methods (1)

method

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.