finding
active
finding:larger-width-students-learn-infrequent-tasks-better-in-k-32-regression-mixture-per-task-loss-tracks-theorem-3-predictionLarger-width students learn infrequent tasks better in K=32 regression mixture; per-task loss tracks Theorem 3 prediction
Fig. 2 verification.
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
- Width buys features in order of utility, so only larger models learn infrequent or complex taskssupportsInterpretation of Theorem 3.
Questions (1)
question
- Motivating question.
Findings (1)
finding
- Fig. 5.
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.
- Hypothesis box in §3.2.
- Core framing.
- Fig. 22.
- Fig. 23.
- Selective pressure toward convergence via task generality
- When task gradient norms differ greatly, large-norm tasks have not converged while small-norm tasks have nearly convergedhypothesis0.778Motivates setting αk = max norm to enable further learning on under-converged tasks
- Extrapolation of scaling predictive models to AGI.
- Synthetic multi-task setup with power-law frequencies and spectra.