The DOI matches its Crossref record; 33 of the 33 references it cites were found in a registry or an index.
From error bounds to the complexity of first-order descent methods for convex functions
Open accessAbstract
This paper shows that error bounds can be used as effective tools for deriving complexity results for first-order descent methods in convex minimization. In a first stage, this objective led us to revisit the interplay between error bounds and the Kurdyka-Łojasiewicz (KL) inequality. One can show the equivalence between the two concepts for convex functions having a moderately flat profile near the set of minimizers (as those of functions with Hölderian growth). A counterexample shows that the equivalence is no longer true for extremely flat functions. This fact reveals the relevance of an approach based on KL inequality. In a second stage, we show how KL inequalities can in turn be employed to compute new complexity bounds for a wealth of descent methods for convex problems. Our approach is completely original and makes use of a one-dimensional worst-case proximal sequence in the spirit of the famous majorant method of Kantorovich. Our result applies to a very simple abstract scheme that covers a wide class of descent methods. As a byproduct of our study, we also provide new results for the globalization of KL inequalities in the convex framework. Our main results inaugurate a simple method: derive an error bound, compute the desingularizing function whenever possible, identify essential constants in the descent method and finally compute the complexity using the one-dimensional worst case proximal sequence. Our method is illustrated through projection methods for feasibility problems, and through the famous iterative shrinkage thresholding algorithm (ISTA), for which we show that the complexity bound is of the form $$O(q^{k})$$O(qk) where the constituents of the bound only depend on error bound constants obtained for an arbitrary least squares objective with $$\ell ^1$$ℓ1 regularization.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
Beck, A., & Teboulle, M. (2009) · SIAM Journal on Imaging Sciences · doi:10.1137/080716542 · Cited by 11,952
An Introduction To Compressive Sampling
Candes, E. J., & Wakin, M. B. (2008) · IEEE Signal Processing Magazine · doi:10.1109/msp.2007.914731 · Cited by 10,017
An iterative thresholding algorithm for linear inverse problems with a sparsity constraint.
Daubechies, I., Defrise, M., & De Mol, C. (2004) · Communications on Pure and Applied Mathematics · doi:10.1002/cpa.20042 · Cited by 4,958
Monotone Operators and the Proximal Point Algorithm
Rockafellar, R. T. (1976) · SIAM Journal on Control and Optimization · doi:10.1137/0314056 · Cited by 3,559
Convex Analysis and Monotone Operator Theory in Hilbert Spaces
Bauschke, H. H., & Combettes, P. L. (2011) · CMS Books in Mathematics · doi:10.1007/978-1-4419-9467-7 · Cited by 2,962
Signal Recovery by Proximal Forward-Backward Splitting
Combettes, P. L., & Wajs, V. R. (2005) · Multiscale Modeling & Simulation · doi:10.1137/050626090 · Cited by 2,678
Proximal Splitting Methods in Signal Processing
Combettes, P. L., & Pesquet, J.-C. (2011) · Springer Optimization and Its Applications · doi:10.1007/978-1-4419-9569-8_10 · Cited by 2,183
Proximal alternating linearized minimization for nonconvex and nonsmooth problems
Bolte, J., Sabach, S., & Teboulle, M. (2014) · Mathematical Programming · doi:10.1007/s10107-013-0701-9 · Cited by 1,688
Self-citationOn Projection Algorithms for Solving Convex Feasibility Problems
Bauschke, H. H., & Borwein, J. M. (1996) · SIAM Review · doi:10.1137/s0036144593251710 · Cited by 1,654
Bochnak, J., Coste, M., & Roy, M.-F. (1998) · Springer · doi:10.1007/978-3-662-03718-8 · Cited by 1,538
Attouch, H., Bolte, J., & Svaiter, B. F. (2013) · Mathematical Programming · doi:10.1007/s10107-011-0484-9 · Cited by 1,414
Self-citation(2014) · Choice Reviews Online · doi:10.5860/choice.51-3296 · Cited by 1,260
Attouch, H., Bolte, J., Redont, P., & Soubeyran, A. (2010) · Mathematics of Operations Research · doi:10.1287/moor.1100.0449 · Cited by 1,172
Self-citationBolte, J., Daniilidis, A., & Lewis, A. (2007) · SIAM Journal on Optimization · doi:10.1137/050644641 · Cited by 671
Self-citationOn the convergence of the proximal algorithm for nonsmooth functions involving analytic features
Attouch, H., & Bolte, J. (2007) · Mathematical Programming · doi:10.1007/s10107-007-0133-5 · Cited by 568
Self-citationOn gradients of functions definable in o-minimal structures
Kurdyka, K. (1998) · Annales de l'Institut Fourier · doi:10.5802/aif.1638 · Cited by 461
Error bounds in mathematical programming
Pang, J.-S. (1997) · Mathematical Programming · doi:10.1007/bf02614322 · Cited by 441
Error bounds and convergence analysis of feasible descent methods: a general approach
Luo, Z.-Q., & Tseng, P. (1993) · Annals of Operations Research · doi:10.1007/bf02096261 · Cited by 420
Sur le problème de la division
Łojasiewicz, S. (1959) · Studia Mathematica · doi:10.4064/sm-18-1-87-136 · Cited by 300
Convergence of the Iterates of Descent Methods for Analytic Cost Functions
Absil, P. A., Mahony, R., & Andrews, B. (2005) · SIAM Journal on Optimization · doi:10.1137/040605266 · Cited by 291
Convex Optimization in Normed Spaces: Theory, Methods and Examples
Peypouquet, J. (2015) · SpringerBriefs in optimization · doi:10.1007/978-3-319-13710-0 · Cited by 239
Self-citationSur la géométrie semi- et sous- analytique
Łojasiewicz, S. (1993) · Annales de l'Institut Fourier · doi:10.5802/aif.1384 · Cited by 203
Frankel, P., Garrigos, G., & Peypouquet, J. (2015) · Journal of Optimization Theory and Applications · doi:10.1007/s10957-014-0642-3 · Cited by 180
Self-citationFinite termination of the proximal point algorithm
Ferris, M. C. (1991) · Mathematical Programming · doi:10.1007/bf01594944 · Cited by 135
A Frank–Wolfe Type Theorem for Convex Polynomial Programs
Belousov, E. G., & Klatte, D. (2002) · Computational Optimization and Applications · doi:10.1023/a:1014813701864 · Cited by 85
Linearly convergent away-step conditional gradient for non-strongly convex functions
Beck, A., & Shtern, S. (2016) · Mathematical Programming · doi:10.1007/s10107-016-1069-4 · Cited by 85
A Condition Number for Differentiable Convex Inequalities
Mangasarian, O. L. (1985) · Mathematics of Operations Research · doi:10.1287/moor.10.2.175 · Cited by 79
Bolte, J., & Pauwels, E. (2016) · Mathematics of Operations Research · doi:10.1287/moor.2015.0735 · Cited by 76
Self-citationOn damped second-order gradient systems
Bégout, P., Bolte, J., & Jendoubi, M. A. (2015) · Journal of Differential Equations · doi:10.1016/j.jde.2015.04.016 · Cited by 50
Self-citationError Bounds for Quadratic Systems
Luo, Z.-Q. T., & Sturm, J. F. (2000) · Applied optimization · doi:10.1007/978-1-4757-3216-0_16 · Cited by 38
Li, G., Mordukhovich, B. S., Nghia, T. T. A., & Phạm, T.-S. (2016) · Mathematical Programming · doi:10.1007/s10107-016-1014-6 · Cited by 28
Global Hölderian Error Bound for Nondegenerate Polynomials
Vui, H. H. (2013) · SIAM Journal on Optimization · doi:10.1137/110859889 · Cited by 27
Penalty functions in subanalytic optimization
Dedieu, J. P. (1992) · Optimization · doi:10.1080/02331939208843840 · Cited by 23
Cited by
Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Łojasiewicz Condition
Karimi, H., Nutini, J., & Schmidt, M. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46128-1_50 · Cited by 824
Metadata
- Authors
- Bolte, J., Nguyen, T. P., Peypouquet, J., & Suter, B. W.
- Venue
- Mathematical Programming
- Published
- 2016-11-30
- Volume
- 165
- Issue
- 2
- Pages
- 471-507
- ISSN
- 0025-5610 (ISSN-L)
- 1436-4646
- OpenAlex
- W2265806316
- Cited by
- 265
- References
- 33
- FWCI
- 25.60
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.