pith. sign in

A.5 Extremal partial trace Lemma A.5.For anyk≤dand two matricesQ∈St d k(R),Σ∈R d×d symmetric positive definite, we have dX i=d−k+1 λi(Σ)≤Tr(Q ⊤ΣQ)≤ kX i=1 λi(Σ).(19) Proof

Lower bound that depends ond x: The proof follows along the same lines as those in the proof of Theorem 4

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

1 Pith paper citing it
browse 1 citing papers

fields

cs.IT 1

years

2025 1

verdicts

UNVERDICTED 1

representative citing papers

Near-optimal Rank Adaptive Inference of High Dimensional Matrices

cs.IT · 2025-10-09 · unverdicted · novelty 6.0

Derives instance-specific lower bounds on sample complexity for rank-adaptive matrix estimation and proposes a least-squares plus universal singular-value-thresholding algorithm whose finite-sample error nearly matches those bounds.

citing papers explorer

Showing 1 of 1 citing paper.

  • Near-optimal Rank Adaptive Inference of High Dimensional Matrices cs.IT · 2025-10-09 · unverdicted · none · ref 47

    Derives instance-specific lower bounds on sample complexity for rank-adaptive matrix estimation and proposes a least-squares plus universal singular-value-thresholding algorithm whose finite-sample error nearly matches those bounds.