pith. sign in

The smallest singular value of a random rectangular matrix

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

1 Pith paper citing it
abstract

We prove an optimal estimate on the smallest singular value of a random subgaussian matrix, valid for all fixed dimensions. For an N by n matrix A with independent and identically distributed subgaussian entries, the smallest singular value of A is at least of the order \sqrt{N} - \sqrt{n-1} with high probability. A sharp estimate on the probability is also obtained.

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Sharp Capacity Scaling of Spectral Optimizers in Learning Associative Memory

cs.LG · 2026-03-27 · unverdicted · novelty 7.0

Muon achieves higher storage capacity than SGD and matches Newton's method in one-step recovery rates for associative memory under power-law distributions, while saturating at larger critical batch sizes and showing faster initial multi-step dynamics.

citing papers explorer

Showing 1 of 1 citing paper.

  • Sharp Capacity Scaling of Spectral Optimizers in Learning Associative Memory cs.LG · 2026-03-27 · unverdicted · none · ref 45 · internal anchor

    Muon achieves higher storage capacity than SGD and matches Newton's method in one-step recovery rates for associative memory under power-law distributions, while saturating at larger critical batch sizes and showing faster initial multi-step dynamics.