Entrywise error bounds for spectral methods on BTL ranking under semi-random adversaries depend on graph spectral properties and can be recovered asymptotically via reweighting to restore the spectral gap.
πβ₯πwith probability at least1βπ(π βπ‘ )
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Entrywise Error Bounds for Spectral Ranking with Semi-Random Adversaries
Entrywise error bounds for spectral methods on BTL ranking under semi-random adversaries depend on graph spectral properties and can be recovered asymptotically via reweighting to restore the spectral gap.