Corpus ID: 222132883

No quantum speedup over gradient descent for non-smooth convex optimization

@article{Garg2020NoQS,
  title={No quantum speedup over gradient descent for non-smooth convex optimization},
  author={Ankit Garg and Robin Kothari and Praneeth Netrapalli and Suhail Sherif},
  journal={ArXiv},
  year={2020},
  volume={abs/2010.01801}
}
  • Ankit Garg, Robin Kothari, +1 author Suhail Sherif
  • Published 2020
  • Mathematics, Computer Science, Physics
  • ArXiv
  • We study the first-order convex optimization problem, where we have black-box access to a (not necessarily smooth) function $f:\mathbb{R}^n \to \mathbb{R}$ and its (sub)gradient. Our goal is to find an $\epsilon$-approximate minimum of $f$ starting from a point that is distance at most $R$ from the true minimum. If $f$ is $G$-Lipschitz, then the classic gradient descent algorithm solves this problem with $O((GR/\epsilon)^{2})$ queries. Importantly, the number of queries is independent of the… CONTINUE READING

    References

    SHOWING 1-10 OF 25 REFERENCES
    Complexity of Highly Parallel Non-Smooth Convex Optimization
    • 13
    • PDF
    Quantum Speed-Ups for Solving Semidefinite Programs
    • 62
    • PDF
    Quantum Algorithms for Learning Symmetric Juntas via the Adversary Bound
    • A. Belovs
    • Mathematics, Physics
    • 2014 IEEE 29th Conference on Computational Complexity (CCC)
    • 2014
    • 18
    • PDF
    Lower Bounds for Parallel and Randomized Convex Optimization
    • 12
    • PDF
    Convex optimization using quantum oracles
    • 16
    • PDF