跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.26055 · v1

When Do Rankings Beat Signs? Gradient Direction Recovery under Even Nuisance

首次提交 2026-11-19 21:01
版本更新 2026-11-19 21:01
雷达观测 2026-11-20 16:53
arXiv ↗PDF ↗

摘要

Can ranking a batch of antipodal query pairs recover a gradient direction with fewer evaluations than using within-pair signs alone? We study fixed-center recovery in dd dimensions for a linear signal plus an unknown differentiable even nuisance, counting function evaluations and feedback rounds separately. Shared pair offsets create an information hierarchy: Mirror retains within-pair signs, Reverse couples reversed cross-pair orders to cancel offsets, and Full enforces all ranking inequalities. Relative shell variation is the nuisance range over the query sphere normalized by the linear-signal scale. When it is at most cε/dc\varepsilon/\sqrt{d}, Reverse localizes every consistent direction to angular accuracy ε\varepsilon using O~(d+d/ε)\widetilde{O}(d+\sqrt{d/\varepsilon}) evaluations in one round at fixed confidence, without a variation bound supplied to the decoder. This matches a lower bound up to logarithmic factors, versus the Θ(d/ε)Θ(d/\varepsilon) one-round sign-only minimax cost on the same class. Over well-conditioned positive-definite quadratics with no common relative-curvature bound, the RR-round minimax cost is instead Θ(dR(ε−1/R−1))Θ(dR(\varepsilon^{-1/R}-1)), even with cumulative rankings. We extend validity beyond exact evenness under supplied error bounds. Matched-endpoint experiments certify information beyond signs and short cycles. On two ridge tasks under joint evaluation and round caps, short-cycle recovery attains lower terminal mean gaps than the tested batch-capable controls. An additional optimization benefit from fitting the complete ranking remains unestablished.

作者备注:51 pages, 7 figures, 14 tables, including appendices

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-19 21:01 · 最新观测版本

When Do Rankings Beat Signs? Gradient Direction Recovery under Even Nuisance

Can ranking a batch of antipodal query pairs recover a gradient direction with fewer evaluations than using within-pair signs alone? We study fixed-center recovery in dd dimensions for a linear signal plus an unknown differentiable even nuisance, counting function evaluations and feedback rounds separately. Shared pair offsets create an information hierarchy: Mirror retains within-pair signs, Reverse couples reversed cross-pair orders to cancel offsets, and Full enforces all ranking inequalities. Relative shell variation is the nuisance range over the query sphere normalized by the linear-signal scale. When it is at most cε/dc\varepsilon/\sqrt{d}, Reverse localizes every consistent direction to angular accuracy ε\varepsilon using O~(d+d/ε)\widetilde{O}(d+\sqrt{d/\varepsilon}) evaluations in one round at fixed confidence, without a variation bound supplied to the decoder. This matches a lower bound up to logarithmic factors, versus the Θ(d/ε)Θ(d/\varepsilon) one-round sign-only minimax cost on the same class. Over well-conditioned positive-definite quadratics with no common relative-curvature bound, the RR-round minimax cost is instead Θ(dR(ε−1/R−1))Θ(dR(\varepsilon^{-1/R}-1)), even with cumulative rankings. We extend validity beyond exact evenness under supplied error bounds. Matched-endpoint experiments certify information beyond signs and short cycles. On two ridge tasks under joint evaluation and round caps, short-cycle recovery attains lower terminal mean gaps than the tested batch-capable controls. An additional optimization benefit from fitting the complete ranking remains unestablished.

查看此版本解读 →查看此版本原文 ↗