按年被提到
20262026 · 2 次2026
算法与数据结构›经典算法与数据结构·arXiv:2607.13335 · math.OC

Closing the Oracle-Complexity Gap in Derivative-Free Convex Optimization: A Near-Quadratic Lower Bound from Exact Function Values

Phillip Kerger · 2026
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2026-07-18 · 最近 2026-10-06
2不同的人
2活跃月份
2讨论串
1被引(OpenAlex)
arXiv 摘要(候选层不写导读)

We study the deterministic query complexity of minimizing a convex Lipschitz function over a $d$-dimensional Euclidean ball using only exact function values. At accuracy $Θ(d^{-1/2})$, the previously applicable lower bound was $Ω(d)$, inherited from the stronger full first-order oracle, while an upper bound from Protasov's value-only method requires $O(d^2\log^2 d)$ evaluations. By providing a lower bound of $Ω(\,\frac{d^2}{\log(d+1)})$ on the oracle complexity in this setting, we thereby close this gap dating back to 1996, up to polylogarithmic factors. Furthermore, we are able to lift this result to the mixed-integer setting: Mixed-integer convex optimization with $d$ continuous and $n$ discrete variables using function values requires $\tildeΩ(d^2\cdot 2^n)$ queries.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论applfanboysbgon · 2026-07

“Two points: - Hasn't been peer reviewed yet, so take with a grain of salt. This applies to all claimed proofs, not just AI-generated ones. Even humans hallucinate proofs too! - The prompt is on page 27 here[1]. It is ten pages of advanced mathematics priming the model in the right direction, apparently informed by a year of prior research. That doesn't …”

GPT-5.6 used a prompt to close a 30-year gap in convex optimization原评论 ↗
评论blt · 2026-10

“Every few years, a derivative-free neural network optimization algorithm gets some hype. I'd bet my life savings that none of them ever make an impact. Derivative-free optimization can be useful for genuinely discontinuous objectives [1], but common neural network objectives are smooth and/or Lipschitz. The gradient is useful. Instead of trying random d…”

Dust: Pretraining Transformers Without Backpropagation原评论 ↗