Abstract
This article is devoted to one particular case of using universal accelerated proximal envelopes to obtain computationally efficient accelerated versions of methods used to solve various optimization problem setups. We propose a proximally accelerated coordinate descent method that achieves the efficient algorithmic complexity of iteration and allows taking advantage of the data sparseness. It was considered an example of applying the proposed approach to optimizing a SoftMax-like function, for which the described method allowing weaken the dependence of the computational complexity on the dimension n in \(\mathcal {O}(\sqrt{n})\) times and, in practice, demonstrates a faster convergence in comparison with standard methods. As an example of applying the proposed approach, it was shown a variant of obtaining on its basis some efficient methods for optimizing Markov Decision Processes (MDP) in a minimax formulation with a Nesterov smoothed target function.
D.A. Pasechnyuk’s research was supported by the A.M. Raigorodsky Scholarship in the field of optimization and RFBR grant 19-31-51001 (Scientific mentoring). The work of V.V. Matyukhin was supported by the Ministry of Science and Higher Education of the Russian Federation (state assignment) No. 075-00337-20-03, project number 0714-2020-0005.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
For the detailed proofs see appendices in full paper version on https://arxiv.org/abs/2103.06688.
References
Anikin, A., et al.: Modern efficient numerical approaches to regularized regression problems in application to traffic demands matrix calculation from link loads. In: Proceedings of International conference ITAS-2015. Russia, Sochi (2015)
Bertsekas, D.P.: Dynamic Programming and Optimal Control. Athena Scientific, Belmont, MA (1995)
Blanchard, P., Higham, D.J., Higham, N.J.: Accurately Computing the Log-Sum-Exp and Softmax Functions (2019)
Bubeck, S.: Convex optimization: algorithms and complexity. arXiv preprint arXiv:1405.4980 (2014)
Bubeck, S., Jiang, Q., Lee, Y.T., Li, Y., Sidford, A.: Near-optimal method for highly smooth convex optimization. In: Conference on Learning Theory, pp. 492–507. PMLR (2019)
Carmon, Y., Jin, Y., Sidford, A., Tian, K.: Variance reduction for matrix games. In: Advances in Neural Information Processing Systems, pp. 11381–11392 (2019)
Carmon, Y., Jin, Y., Sidford, A., Tian, K.: Coordinate methods for matrix games. arXiv preprint arXiv:2009.08447 (2020)
Chernov, A.: Direct-dual method for solving the entropy-linear programming problem. Intell. Syst. Theor Appl. 20(1), 39–59 (2016)
d’Aspremont, A., Scieur, D., Taylor, A.: Acceleration methods (2021)
Doikov, N., Nesterov, Y.: Contracting proximal methods for smooth convex optimization. SIAM J. Optim. 30(4), 3146–3169 (2020)
Dvinskikh, D., et al.: Accelerated meta-algorithm for convex optimization. arXiv preprint arXiv:2004.08691 (2020)
Gasnikov, A., Gasnikova, E., Nesterov, Y., Chernov, A.: Efficient numerical methods for entropy-linear programming problems. Comput. Math. Math. Phys. 56(4), 523–534 (2016)
Gasnikov, A.: Universal gradient descent. arXiv preprint arXiv:1711.00394 (2017)
Ivanova, A., Pasechnyuk, D., Grishchenko, D., Shulgin, E., Gasnikov, A., Matyukhin, V.: Adaptive catalyst for smooth convex optimization. arXiv preprint arXiv:1911.11271 (2019)
Jin, Y., Sidford, A.: Efficiently solving MDPs with stochastic mirror descent. In: International Conference on Machine Learning, pp. 4890–4900. PMLR (2020)
Kamzolov, D., Gasnikov, A., Dvurechensky, P.: On the optimal combination of tensor optimization methods. arXiv preprint arXiv:2002.01004 (2020)
Kulunchakov, A., Mairal, J.: A generic acceleration framework for stochastic composite optimization. In: Advances in Neural Information Processing Systems. pp. 12556–12567 (2019)
Lin, H., Mairal, J., Harchaoui, Z.: A universal catalyst for first-order optimization. Adv. Neural Inf. Process. Syst. 28, 3384–3392 (2015)
Lin, H., Mairal, J., Harchaoui, Z.: Catalyst acceleration for first-order convex optimization: from theory to practice. J. Mach. Learn. Res. 18(1), 7854–7907 (2017)
Monteiro, R.D., Svaiter, B.F.: An accelerated hybrid proximal extragradient method for convex optimization and its implications to second-order methods. SIAM J. Optim. 23(2), 1092–1125 (2013)
Nesterov, Y.: Smooth minimization of non-smooth functions. Math. Program. 103(1), 127–152 (2005)
Nesterov, Y.: Efficiency of coordinate descent methods on huge-scale optimization problems. SIAM J. Optim. 22(2), 341–362 (2012)
Nesterov, Y.: Lectures on Convex Optimization. SOIA, vol. 137. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-91578-4
Nesterov, Y., Stich, S.U.: Efficiency of the accelerated coordinate descent method on structured optimization problems. SIAM J. Optim. 27(1), 110–123 (2017)
Paquette, C., Lin, H., Drusvyatskiy, D., Mairal, J., Harchaoui, Z.: Catalyst acceleration for gradient-based non-convex optimization. arXiv preprint arXiv:1703.10993 (2017)
Parikh, N., Boyd, S.: Proximal algorithms. Found. Trends Optim 1(3), 127–239 (2014)
Rockafellar, R.T.: Monotone operators and the proximal point algorithm. SIAM j. Control Optim. 14(5), 877–898 (1976)
SciPy.org: Python Scipy documentation: scipy.sparse.csr\_matrix (2020) https://docs.scipy.org/doc/scipy/reference/generated/scipy.sparse.csr_matrix.html. Accessed 5 Jan 2021
Sidford, A., Wang, M., Wu, X., Ye, Y.: Variance reduced value iteration and faster algorithms for solving Markov decision processes. In: Proceedings of the Twenty-Ninth Annual ACM-SIAM Symposium on Discrete Algorithms. pp. 770–787. SIAM (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Pasechnyuk, D., Matyukhin, V. (2021). On the Computational Efficiency of Catalyst Accelerated Coordinate Descent. In: Pardalos, P., Khachay, M., Kazakov, A. (eds) Mathematical Optimization Theory and Operations Research. MOTOR 2021. Lecture Notes in Computer Science(), vol 12755. Springer, Cham. https://doi.org/10.1007/978-3-030-77876-7_12
Download citation
DOI: https://doi.org/10.1007/978-3-030-77876-7_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-77875-0
Online ISBN: 978-3-030-77876-7
eBook Packages: Computer ScienceComputer Science (R0)