finding
active
finding:with-wide-complexity-range-2-12-learning-order-is-non-monotonic-in-frequency-because-a-complex-task-s-third-mode-can-outrank-frequent-tasks-higher-modesWith wide complexity range [2,12], learning order is non-monotonic in frequency because a complex task's third mode can outrank frequent tasks' higher modes
Fig. 13.
Source paper
extracted_from(2026) · Jing Huang · Daniel Wurgaft · Rachit Bansal · Laura Ruis +5
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Frequency alone is insufficient to predict learning order; both frequency and complexity are neededsupportsFrom complexity sweeps.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Discrete case.
- Fig. 7.
- Fig. 22.
- When task gradient norms differ greatly, large-norm tasks have not converged while small-norm tasks have nearly convergedhypothesis0.758Motivates setting αk = max norm to enable further learning on under-converged tasks
- Extends the brutal geometry thesis beyond architecture into all creative and social domains; acknowledged as not yet confirmed with certainty
- Scale alone is not the mechanism enabling rare-task learning; multi-task methods can also enable itclaim0.750Clarification in related work.
- Baseline.
- Claims middle-range order is universal in biology and implies a reliable generative process exists