Outlier Detection in Regression: Conic Quadratic Formulations

References

• Agulló J (2001) New algorithms for computing the least trimmed squares regression estimator. Comput. Statist. Data Anal. 36(4):425–439.Crossref, Google Scholar
• Aktürk MS, Atamtürk A, Gürel S (2009) A strong conic quadratic reformulation for machine-job assignment with controllable processing times. Oper. Res. Lett. 37(3):187–191.Crossref, Google Scholar
• Atamturk A, Gómez A (2020) Safe screening rules for L0-regression from perspective relaxations. Daumé H III, Singh A, eds. Proc. 37th Internat. Conf. Machine Learn. (PMLR, Cambridge, MA), 421–430.Google Scholar
• Atamtürk A, Gómez A (2025) Rank-one convexification for sparse regression. J. Machine Learn. Res. 26(35):1–50.Google Scholar
• Atamtürk A, Gómez A, Han S (2021) Sparse and smooth signal estimation: Convexification of L0-formulations. J. Machine Learn. Res. 22(1):2370–2412.Google Scholar
• Ben-Ameur W, Neto J (2022) New bounds for subset selection from conic relaxations. Eur. J. Oper. Res. 298(2):425–438.Crossref, Google Scholar
• Bernholt T (2005a) Robust estimators are hard to compute. Technical report, University of Dortmund, Dortmund, Germany.Google Scholar
• Bernholt T (2005b) Computing the least median of squares estimator in time O(nd). Gervasi O, Gavrilova ML, Kumar V, Laganà A, Lee HP, Mun Y, Taniar D, Tan CJK, eds. Comput. Sci. Its Appl. ICCSA 2005 (Springer, Berlin), 697–706.Google Scholar
• Bertsimas D, Mazumder R (2014) Least quantile regression via modern optimization. Ann. Statist. 42(6):2494–2525.Crossref, Google Scholar
• Bertsimas D, Van Parys B (2020) Sparse high-dimensional regression: Exact scalable algorithms and phase transitions. Ann. Statist. 48(1):300–323.Crossref, Google Scholar
• Bertsimas D, King A, Mazumder R (2016) Best subset selection via a modern optimization lens. Ann. Statist. 44(2):813–852.Crossref, Google Scholar
• Bhatia K, Jain P, Kar P (2015) Robust regression via hard thresholding. Cortes C, Lawrence N, Lee D, Sugiyama M, Garnett R, eds. Adv. Neural Inform. Processing Systems 28 (NIPS 2015) (Curran Associates, Inc., Red Hook, NY), 721–729.Google Scholar
• Cozad A, Sahinidis NV, Miller DC (2014) Learning surrogate models for simulation-based optimization. AIChE J. 60(6):2211–2227.Crossref, Google Scholar
• Cozad A, Sahinidis NV, Miller DC (2015) A combined first-principles and data-driven approach to model building. Comput. Chemical Engrg. 73:116–127.Crossref, Google Scholar
• Dong H, Chen K, Linderoth J (2015) Regularization vs. relaxation: A conic optimization perspective of statistical variable selection. Preprint, submitted October 20, https://arxiv.org/abs/1510.06083.Google Scholar
• El Ghaoui L, Lebret H (1997) Robust solutions to least-squares problems with uncertain data. SIAM J. Matrix Anal. Appl. 18(4):1035–1064.Crossref, Google Scholar
• Frangioni A, Gentile C (2006) Perspective cuts for a class of convex 0–1 mixed integer programs. Math. Programming 106:225–236.Crossref, Google Scholar
• Giloni A, Padberg M (2002) Least trimmed squares regression, least median squares regression, and mathematical programming. Math. Comput. Model. 35(9–10):1043–1060.Crossref, Google Scholar
• Gómez A (2021) Outlier detection in time series via mixed-integer conic quadratic optimization. SIAM J. Optim. 31(3):1897–1925.Crossref, Google Scholar
• Gómez A, Neto J (2025) Outlier detection in regression: Conic quadratic formulations. https://doi.org/10.1287/ijoc.2025.1215.cd, https://github.com/INFORMSJoC/2025.1215.Google Scholar
• Gómez A, Prokopyev OA (2021) A mixed-integer fractional optimization approach to best subset selection. INFORMS J. Comput. 33(2):551–565.Abstract, Google Scholar
• Günlük O, Linderoth J (2010) Perspective reformulations of mixed integer nonlinear programs with indicator variables. Math. Programming 124:183–205.Crossref, Google Scholar
• Hampel FR (1971) A general qualitative definition of robustness. Ann. Math. Statist. 42(6):1887–1896.Crossref, Google Scholar
• Hawkins DM (1994) The feasible solution algorithm for least trimmed squares regression. Comput. Statist. Data Anal. 17(2):185–196.Crossref, Google Scholar
• Hazimeh H, Mazumder R (2020) Fast best subset selection: Coordinate descent and local combinatorial optimization algorithms. Oper. Res. 68(5):1517–1537.Link, Google Scholar
• Hazimeh H, Mazumder R, Nonet T (2022a) L0Learn: A scalable package for sparse learning using L0 regularization. Preprint, submitted February 10, https://arxiv.org/abs/2202.04820.Google Scholar
• Hazimeh H, Mazumder R, Saab A (2022b) Sparse regression at scale: Branch-and-bound rooted in first-order optimization. Math. Programming 196(1–2):347–388.Crossref, Google Scholar
• Huber PJ (1973) Robust regression: Asymptotics, conjectures and Monte Carlo. Ann. Statist. 1(5):799–821.Crossref, Google Scholar
• Huber PJ (2011) Robust Statistics (Springer, Berlin).Google Scholar
• Insolia L, Kenney A, Chiaromonte F, Felici G (2022) Simultaneous feature selection and outlier detection with optimality guarantees. Biometrics 78(4):1592–1603.Crossref, Google Scholar
• Kimura K, Waki H (2018) Minimization of Akaike’s information criterion in linear regression analysis via mixed integer nonlinear program. Optim. Methods Software 33(3):633–649.Crossref, Google Scholar
• Liu P, Fattahi S, Gómez A, Küçükyavuz S (2022) A graph-based decomposition method for convex quadratic optimization with indicators. Math. Programming 200:669–701.Crossref, Google Scholar
• Manzour H, Küçükyavuz S, Wu H-H, Shojaie A (2021) Integer programming for learning directed acyclic graphs from continuous data. INFORMS J. Optim. 3(1):46–73.Link, Google Scholar
• Mazumder R, Radchenko P, Dedieu A (2023) Subset selection with shrinkage: Sparse linear modeling when the SNR is low. Oper. Res. 71(1):129–147.Link, Google Scholar
• Miyashiro R, Takano Y (2015) Mixed integer second-order cone programming formulations for variable selection in linear regression. Eur. J. Oper. Res. 247(3):721–731.Crossref, Google Scholar
• Mount DM, Netanyahu NS, Piatko CD, Silverman R, Wu AY (2014) On the least trimmed squares estimator. Algorithmica 69:148–183.Crossref, Google Scholar
• Park YW, Klabjan D (2020) Subset selection for multiple linear regression via optimization. J. Global Optim. 77(3):543–574.Crossref, Google Scholar
• Rousseeuw PJ (1984) Least median of squares regression. J. Amer. Statist. Assoc. 79(388):871–880.Crossref, Google Scholar
• Rousseeuw PJ, Leroy AM (1987) Robust Regression and Outlier Detection (John Wiley & Sons, New York).Crossref, Google Scholar
• Rousseeuw PJ, Van Driessen K (2006) Computing LTS regression for large data sets. Data Mining Knowledge Discovery 12:29–45.Crossref, Google Scholar
• Rousseeuw P, Yohai V (1984) Robust regression by means of S-estimators. Franke J, Härdle W, Martin D, eds. Robust Nonlinear Time Series Anal. (Springer-Verlag, Berlin), 256–272.Google Scholar
• Rousseeuw P, Croux C, Todorov V, Ruckstuhl A, Salibian-Barrera M, Verbeke T, Koller M, Maechler M (2009) Robustbase: Basic robust statistics. R package version 0.4-5. Accessed November 8, 2025, http://CRAN.R-project.org/package=robustbase.Google Scholar
• She Y, Owen AB (2011) Outlier detection using nonconvex penalized regression. J. Amer. Statist. Assoc. 106(494):626–639.Crossref, Google Scholar
• Shen Y, Sanghavi S (2019a) Iterative least trimmed squares for mixed linear regression. Wallach H, Larochelle H, Beygelzimer A, d’Alché-Buc F, Fox E, Garnett R, eds. Adv. Neural Inform. Processing Systems 32 (Curran Associates, Inc., Red Hook, NY), 6078–6088.Google Scholar
• Shen Y, Sanghavi S (2019b) Learning with bad training data via iterative trimmed loss minimization. Chaudhuri K, Salakhutdinov R, eds. Proc. 36th Internat. Conf. Machine Learn. (PMLR, Cambridge, MA), 5739–5748.Google Scholar
• Wilson ZT, Sahinidis NV (2017) The ALAMO approach to machine learning. Comput. Chemical Engrg. 106:785–795.Crossref, Google Scholar
• Xie W, Deng X (2020) Scalable algorithms for the sparse ridge regression. SIAM J. Optim. 30(4):3359–3386.Crossref, Google Scholar
• Zheng X, Sun X, Li D (2014) Improving the performance of MIQP solvers for quadratic programs with cardinality and minimum threshold constraints: A semidefinite program approach. INFORMS J. Comput. 26(4):690–703.Link, Google Scholar
• Zioutas G, Avramidis A (2005) Deleting outliers in robust regression with mixed integer programming. Acta Math. Appl. Sinica 21:323–334.Crossref, Google Scholar
• Zioutas G, Pitsoulis L, Avramidis A (2009) Quadratic mixed integer programming and support vectors for deleting outliers in robust regression. Ann. Oper. Res. 166(1):339–353.Crossref, Google Scholar