Overview

Oracle complexity measures the number of calls an algorithm needs when it can access a problem only through responses such as gradients, stochastic samples, membership answers, or proximal updates. Researchers develop algorithms and matching lower bounds for settings including convex and nonconvex optimization, online learning, monotone inclusions, and sampling, using methods such as variance reduction, proximal iterations, and higher-order updates. A central finding is that query costs depend not only on accuracy and dimension, but also on randomness, memory, oracle fidelity, and the cost or strength of each response. For many settings upper and lower bounds now match, while gaps remain across oracle models and regimes, including how to trade query budgets against wall-clock cost or memory.

Latest papers

CardsList

35 papers4 papers in the last four weeks, down 67% on the four weeks before. 0.0% of all new papers.

  1. Lower Bounds and Proximally Anchored SGD for Non-Convex Minimization Under Unbounded Variance

    Apr 17, 2026Arda Fazla, Ege C. Kaya, Antesh Upadhyay +1Stochastic OptimizationOracle Complexity

  2. Turing or Cantor: That is the Question

    Apr 12, 2026Eugene EberbachOracle Complexity

  3. Mini-Batch Covariance, Diffusion Limits, and Oracle Complexity in Stochastic Gradient Descent: A Sampling-Design Perspective

    Mar 2, 2026Daniel Zantedeschi, Kumar MuthuramanStochastic Gradient DescentStochastic Optimization Convergence

  4. On the Gradient Complexity of Private Optimization with Private Oracles

    Nov 17, 2025Michael Menart, Aleksandar NikolovQuery ComplexityOracle Complexity