The Multi-Query Paradox in Zeroth-Order Optimization

• URL: http://arxiv.org/abs/2509.15552v2
• Date: Mon, 29 Sep 2025 02:52:34 GMT
• Title: The Multi-Query Paradox in Zeroth-Order Optimization
• Authors: Wei Lin, Qingyu Song, Hong Xu,
• Abstract summary: Zeroth-order Alignment (ZO) provides a powerful framework for problems where explicit gradients are unavailable and have to be approximated using only queries to function.
• Score: 6.777975824808536
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Zeroth-order (ZO) optimization provides a powerful framework for problems where explicit gradients are unavailable and have to be approximated using only queries to function value. The prevalent single-query approach is simple, but suffers from high estimation variance, motivating a multi-query paradigm to improves estimation accuracy. This, however, creates a critical trade-off: under a fixed budget of queries (i.e. cost), queries per iteration and the total number of optimization iterations are inversely proportional to one another. How to best allocate this budget is a fundamental, under-explored question. This work systematically resolves this query allocation problem. We analyze two aggregation methods: the de facto simple averaging (ZO-Avg), and a new Projection Alignment method (ZO-Align) we derive from local surrogate minimization. By deriving convergence rates for both methods that make the dependence on the number of queries explicit across strongly convex, convex, non-convex, and stochastic settings, we uncover a stark dichotomy: For ZO-Avg, we prove that using more than one query per iteration is always query-inefficient, rendering the single-query approach optimal. On the contrary, ZO-Align generally performs better with more queries per iteration, resulting in a full-subspace estimation as the optimal approach. Thus, our work clarifies that the multi-query problem boils down to a choice not about an intermediate query size, but between two classic algorithms, a choice dictated entirely by the aggregation method used. These theoretical findings are also consistently validated by extensive experiments.

Related papers

• Closing the Approximation Gap of Partial AUC Optimization: A Tale of Two Formulations [121.39938773554523]
  The Area Under the ROC Curve (AUC) is a pivotal evaluation metric in real-world scenarios with both class imbalance and decision constraints.<n>We present two simple instance-wise minimax reformulations to close the approximation gap of PAUC optimization.<n>The resulting algorithms enjoy a linear per-iteration computational complexity w.r.t. the sample size and a convergence rate of $O(-2/3)$ for typical one-way and two-way PAUCs.
  arXiv  Detail & Related papers  (2025-12-01T02:52:33Z)
• Towards Fast Algorithms for the Preference Consistency Problem Based on Hierarchical Models [4.007697401483925]
  We construct and compare algorithmic approaches to solve the Consistency Problem for preference statements based on hierarchical models. An instance is consistent if there exists an hierarchical model on the evaluation functions that induces an order relation on the alternatives. We develop three approaches to solve this decision problem.
  arXiv  Detail & Related papers  (2024-10-31T13:48:46Z)
• Training Greedy Policy for Proposal Batch Selection in Expensive Multi-Objective Combinatorial Optimization [52.80408805368928]
  We introduce a novel greedy-style subset selection algorithm for batch acquisition. Our experiments on the red fluorescent proteins show that our proposed method achieves the baseline performance in 1.69x fewer queries.
  arXiv  Detail & Related papers  (2024-06-21T05:57:08Z)
• l1-norm regularized l1-norm best-fit lines [3.0963566281269594]
  We present a novel fitting procedure, utilizing simple ratios and sorting techniques. The proposed algorithm demonstrates a worst-case time complexity of $O$(n2 m log n)$ and, in certain instances, achieves global optimality for the sparse subspace.
  arXiv  Detail & Related papers  (2024-02-26T16:30:58Z)
• RIGA: A Regret-Based Interactive Genetic Algorithm [14.388696798649658]
  We propose an interactive genetic algorithm for solving multi-objective optimization problems under preference imprecision. Our algorithm, called RIGA, can be applied to any multi-objective optimization problem provided that the aggregation function is linear in its parameters. For several performance indicators (computation times, gap to optimality and number of queries), RIGA obtains better results than state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2023-11-10T13:56:15Z)
• Explicit Second-Order Min-Max Optimization Methods with Optimal Convergence Guarantee [86.05440220344755]
  We propose and analyze inexact regularized Newton-type methods for finding a global saddle point of emphcon unconstrained min-max optimization problems. We show that the proposed methods generate iterates that remain within a bounded set and that the iterations converge to an $epsilon$-saddle point within $O(epsilon-2/3)$ in terms of a restricted function.
  arXiv  Detail & Related papers  (2022-10-23T21:24:37Z)
• Multi-block-Single-probe Variance Reduced Estimator for Coupled Compositional Optimization [49.58290066287418]
  We propose a novel method named Multi-block-probe Variance Reduced (MSVR) to alleviate the complexity of compositional problems. Our results improve upon prior ones in several aspects, including the order of sample complexities and dependence on strongity.
  arXiv  Detail & Related papers  (2022-07-18T12:03:26Z)
• Outlier-Robust Sparse Estimation via Non-Convex Optimization [73.18654719887205]
  We explore the connection between high-dimensional statistics and non-robust optimization in the presence of sparsity constraints. We develop novel and simple optimization formulations for these problems. As a corollary, we obtain that any first-order method that efficiently converges to station yields an efficient algorithm for these tasks.
  arXiv  Detail & Related papers  (2021-09-23T17:38:24Z)
• A Retrospective Approximation Approach for Smooth Stochastic Optimization [0.2867517731896504]
  Gradient (SG) is the defactorandom iterative technique to solve optimization (SO) problems with a smooth (non-fimation) objective $imation.
  arXiv  Detail & Related papers  (2021-03-07T16:29:36Z)
• Recent Theoretical Advances in Non-Convex Optimization [56.88981258425256]
  Motivated by recent increased interest in analysis of optimization algorithms for non- optimization in deep networks and other problems in data, we give an overview of recent results of theoretical optimization algorithms for non- optimization.
  arXiv  Detail & Related papers  (2020-12-11T08:28:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.