TY - JOUR A1 - Sagnol, Guillaume A1 - Pauwels, Edouard T1 - An unexpected connection between Bayes A-optimal designs and the group lasso JF - Statistical Papers N2 - We show that the A-optimal design optimization problem over m design points in R^n is equivalent to minimizing a quadratic function plus a group lasso sparsity inducing term over n x m real matrices. This observation allows to describe several new algorithms for A-optimal design based on splitting and block coordinate decomposition. These techniques are well known and proved powerful to treat large scale problems in machine learning and signal processing communities. The proposed algorithms come with rigorous convergence guarantees and convergence rate estimate stemming from the optimization literature. Performances are illustrated on synthetic benchmarks and compared to existing methods for solving the optimal design problem. Y1 - 2019 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:0297-zib-73059 VL - 60 IS - 2 SP - 215 EP - 234 ER - TY - GEN A1 - Duarte, Belmiro P.M. A1 - Sagnol, Guillaume A1 - Wong, Weng Kee T1 - An algorithm based on Semidefinite Programming for finding minimax optimal designs N2 - An algorithm based on a delayed constraint generation method for solving semi-infinite programs for constructing minimax optimal designs for nonlinear models is proposed. The outer optimization level of the minimax optimization problem is solved using a semidefinite programming based approach that requires the design space be discretized. A nonlinear programming solver is then used to solve the inner program to determine the combination of the parameters that yields the worst-case value of the design criterion. The proposed algorithm is applied to find minimax optimal designs for the logistic model, the flexible 4-parameter Hill homoscedastic model and the general nth order consecutive reaction model, and shows that it (i) produces designs that compare well with minimax $D-$optimal designs obtained from semi-infinite programming method in the literature; (ii) can be applied to semidefinite representable optimality criteria, that include the common A-, E-,G-, I- and D-optimality criteria; (iii) can tackle design problems with arbitrary linear constraints on the weights; and (iv) is fast and relatively easy to use. T3 - ZIB-Report - 18-01 KW - Cutting plane algorithm KW - Design efficiency KW - Equivalence theorem KW - Model-based optimal design KW - Nonlinear programming Y1 - 2017 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:0297-zib-66249 SN - 1438-0064 ER - TY - GEN A1 - Duarte, Belmiro P.M. A1 - Sagnol, Guillaume T1 - Approximate and exact D-optimal designs for $2^k$ factorial experiments for Generalized Linear Models via SOCP N2 - We propose (Mixed Integer) Second Order Cone Programming formulations to find approximate and exact $D-$optimal designs for $2^k$ factorial experiments for Generalized Linear Models (GLMs). Locally optimal designs are addressed with Second Order Cone Programming (SOCP) and Mixed Integer Second Order Cone Programming (MISOCP) formulations. The formulations are extended for scenarios of parametric uncertainty employing the Bayesian framework for \emph{log det} $D-$optimality criterion. A quasi Monte-Carlo sampling procedure based on the Hammersley sequence is used for integrating the optimality criterion in the parametric region. The problems are solved in \texttt{GAMS} environment using \texttt{CPLEX} solver. We demonstrate the application of the algorithm with the logistic, probit and complementary log-log models and consider full and fractional factorial designs. T3 - ZIB-Report - 18-02 Y1 - 2017 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:0297-zib-66256 SN - 1438-0064 ER - TY - JOUR A1 - Duarte, Belmiro A1 - Sagnol, Guillaume T1 - Approximate and exact optimal designs for 2^k factorial experiments for generalized linear models via second order cone programming JF - Statistical Papers N2 - Model-based optimal designs of experiments (M-bODE) for nonlinear models are typically hard to compute. The literature on the computation of M-bODE for nonlinear models when the covariates are categorical variables, i.e. factorial experiments, is scarce. We propose second order cone programming (SOCP) and Mixed Integer Second Order Programming (MISOCP) formulations to find, respectively, approximate and exact A- and D-optimal designs for 2𝑘 factorial experiments for Generalized Linear Models (GLMs). First, locally optimal (approximate and exact) designs for GLMs are addressed using the formulation of Sagnol (J Stat Plan Inference 141(5):1684–1708, 2011). Next, we consider the scenario where the parameters are uncertain, and new formulations are proposed to find Bayesian optimal designs using the A- and log det D-optimality criteria. A quasi Monte-Carlo sampling procedure based on the Hammersley sequence is used for computing the expectation in the parametric region of interest. We demonstrate the application of the algorithm with the logistic, probit and complementary log–log models and consider full and fractional factorial designs. Y1 - 2020 U6 - https://doi.org/10.1007/s00362-018-01075-7 VL - 61 SP - 2737 EP - 2767 ER - TY - CHAP A1 - Sagnol, Guillaume T1 - Network-related problems in optimal experimental design and second order cone programming T2 - Proceedings of PROBASTAT'2011, Tatra Mountains Mathematical Publications N2 - In the past few years several applications of optimal experimental designs have emerged to optimize the measurements in communication networks. The optimal design problems arising from this kind of applications share three interesting properties: (i) measurements are only available at a small number of locations of the network; (ii) each monitor can simultaneously measure several quantities, which can be modeled by ``multiresponse experiments"; (iii) the observation matrices depend on the topology of the network. In this paper, we give an overview of these experimental design problems and recall recent results for the computation of optimal designs by Second Order Cone Programming (SOCP). New results for the network-monitoring of a discrete time process are presented. In particular, we show that the optimal design problem for the monitoring of an AR1 process can be reduced to the standard form and we give experimental results. Y1 - 2012 U6 - https://doi.org/10.2478/v10127-012-0016-x VL - 51 SP - 161 EP - 171 ER - TY - JOUR A1 - Sagnol, Guillaume T1 - On the semidefinite representation of real functions applied to symmetric matrices JF - Linear Algebra and its Applications N2 - We present a new semidefinite representation for the trace of a real function f applied to symmetric matrices, when a semidefinite representation of the convex function f is known. Our construction is intuitive, and yields a representation that is more compact than the previously known one. We also show with the help of matrix geometric means and the Riemannian metric of the set of positive definite matrices that for a rational number p in the interval (0,1], the matrix X raised to the exponent p is the largest element of a set represented by linear matrix inequalities. We give numerical results for a problem inspired from the theory of experimental designs, which show that the new semidefinite programming formulation yields a speed-up factor in the order of 10. Y1 - 2013 U6 - https://doi.org/10.1016/j.laa.2013.08.021 VL - 439 IS - 10 SP - 2829 EP - 2843 ER - TY - JOUR A1 - Sagnol, Guillaume T1 - Approximation of a maximum-submodular-coverage problem involving spectral functions, with application to experimental designs JF - Discrete Applied Mathematics N2 - We study a family of combinatorial optimization problems defined by a parameter $p\in[0,1]$, which involves spectral functions applied to positive semidefinite matrices, and has some application in the theory of optimal experimental design. This family of problems tends to a generalization of the classical maximum coverage problem as $p$ goes to $0$, and to a trivial instance of the knapsack problem as $p$ goes to $1$. In this article, we establish a matrix inequality which shows that the objective function is submodular for all $p\in[0,1]$, from which it follows that the greedy approach, which has often been used for this problem, always gives a design within $1-1/e$ of the optimum. We next study the design found by rounding the solution of the continuous relaxed problem, an approach which has been applied by several authors. We prove an inequality which generalizes a classical result from the theory of optimal designs, and allows us to give a rounding procedure with an approximation factor which tends to $1$ as $p$ goes to $1$. Y1 - 2013 U6 - https://doi.org/10.1016/j.dam.2012.07.016 VL - 161 IS - 1-2 SP - 258 EP - 276 ER - TY - JOUR A1 - Sagnol, Guillaume T1 - A class of Semidefinite Programs with rank-one solutions JF - Linear Algebra and its Applications N2 - We show that a class of semidefinite programs (SDP) admits a solution that is a positive semidefinite matrix of rank at most $r$, where $r$ is the rank of the matrix involved in the objective function of the SDP. The optimization problems of this class are semidefinite packing problems, which are the SDP analogs to vector packing problems. Of particular interest is the case in which our result guarantees the existence of a solution of rank one: we show that the computation of this solution actually reduces to a Second Order Cone Program (SOCP). We point out an application in statistics, in the optimal design of experiments. Y1 - 2011 U6 - https://doi.org/10.1016/j.laa.2011.03.027 VL - 435 IS - 6 SP - 1446 EP - 1463 ER - TY - GEN A1 - Sagnol, Guillaume A1 - Harman, Radoslav T1 - Computing exact D-optimal designs by mixed integer second order cone programming N2 - Let the design of an experiment be represented by an $s$-dimensional vector $\vec{w}$ of weights with non-negative components. Let the quality of $\vec{w}$ for the estimation of the parameters of the statistical model be measured by the criterion of $D$-optimality defined as the $m$-th root of the determinant of the information matrix $M(\vec{w})=\sum_{i=1}^s w_iA_iA_i^T$, where $A_i$, $i=1,...,s$, are known matrices with $m$ rows. In the paper, we show that the criterion of $D$-optimality is second-order cone representable. As a result, the method of second order cone programming can be used to compute an approximate $D$-optimal design with any system of linear constraints on the vector of weights. More importantly, the proposed characterization allows us to compute an \emph{exact} $D$-optimal design, which is possible thanks to high-quality branch-and-cut solvers specialized to solve mixed integer second order cone problems. We prove that some other widely used criteria are also second order cone representable, for instance the criteria of $A$-, and $G$-optimality, as well as the criteria of $D_K$- and $A_K$-optimality, which are extensions of $D$-, and $A$-optimality used in the case when only a specific system of linear combinations of parameters is of interest. We present several numerical examples demonstrating the efficiency and universality of the proposed method. We show that in many cases the mixed integer second order cone programming approach allows us to find a provably optimal exact design, while the standard heuristics systematically miss the optimum. T3 - ZIB-Report - 13-39 KW - Optimal Design of Experiments KW - D-optimality KW - SOCP Representability KW - Exact Designs Y1 - 2013 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:0297-zib-41932 SN - 1438-0064 ER - TY - GEN A1 - Sagnol, Guillaume T1 - Picos Documentation. Release 0.1.1. N2 - PICOS is a user friendly interface to several conic and integer programming solvers, very much like YALMIP under MATLAB. The main motivation for PICOS is to have the possibility to enter an optimization problem as a high level model, and to be able to solve it with several different solvers. Multidimensional and matrix variables are handled in a natural fashion, which makes it painless to formulate a SDP or a SOCP. This is very useful for educational purposes, and to quickly implement some models and test their validity on simple examples. Furthermore, with PICOS you can take advantage of the python programming language to read and write data, construct a list of constraints by using python list comprehensions, take slices of multidimensional variables, etc. T3 - ZIB-Report - 12-48 KW - mathematical programming KW - SDP KW - SOCP KW - python Y1 - 2012 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:0297-zib-17396 SN - 1438-0064 ER - TY - JOUR A1 - Sagnol, Guillaume A1 - Harman, Radoslav T1 - Computing exact D-optimal designs by mixed integer second-order cone programming JF - The Annals of Statistics N2 - Let the design of an experiment be represented by an $s-$dimensional vector $w$ of weights with nonnegative components. Let the quality of $w$ for the estimation of the parameters of the statistical model be measured by the criterion of $D-$optimality, defined as the $m$th root of the determinant of the information matrix $M(w)=\sum_{i=1}^s w_i A_i A_i^T$, where $A_i$,$i=1,\ldots,s$ are known matrices with $m$ rows. In this paper, we show that the criterion of $D-$optimality is second-order cone representable. As a result, the method of second-order cone programming can be used to compute an approximate $D-$optimal design with any system of linear constraints on the vector of weights. More importantly, the proposed characterization allows us to compute an exact $D-$optimal design, which is possible thanks to high-quality branch-and-cut solvers specialized to solve mixed integer second-order cone programming problems. Our results extend to the case of the criterion of $D_K-$optimality, which measures the quality of $w$ for the estimation of a linear parameter subsystem defined by a full-rank coefficient matrix $K$. We prove that some other widely used criteria are also second-order cone representable, for instance, the criteria of $A-$, $A_K$-, $G-$ and $I-$optimality. We present several numerical examples demonstrating the efficiency and general applicability of the proposed method. We show that in many cases the mixed integer second-order cone programming approach allows us to find a provably optimal exact design, while the standard heuristics systematically miss the optimum. Y1 - 2015 U6 - https://doi.org/10.1214/15-AOS1339 VL - 43 IS - 5 SP - 2198 EP - 2224 ER - TY - CHAP A1 - Duarte, Belmiro P.M. A1 - Sagnol, Guillaume A1 - Oliveira, Nuno M.C. T1 - A Robust Minimax Semidefinite Programming Formulation for Optimal Design of Experiments for Model Parametrization T2 - 12th International Symposium on Process Systems Engineering and 25th European Symposium on Computer Aided Process Engineering N2 - Model-based optimal design of experiments (M-bODE) is a crucial step in model parametrization since it encloses a framework that maximizes the amount of information extracted from a battery of lab experiments. We address the design of M-bODE for dynamic models considering a continuous representation of the design. We use Semidefinite Programming (SDP) to derive robust minmax formulations for nonlinear models, and extend the formulations to other criteria. The approaches are demonstrated for a CSTR where a two-step reaction occurs. Y1 - 2015 U6 - https://doi.org/10.1016/B978-0-444-63578-5.50146-8 VL - 37 SP - 905 EP - 910 ER - TY - JOUR A1 - Duarte, Belmiro P.M. A1 - Sagnol, Guillaume A1 - Wong, Weng Kee T1 - An algorithm based on Semidefinite Programming for finding minimax optimal designs JF - Computational Statistics & Data Analysis Y1 - 2018 U6 - https://doi.org/10.1016/j.csda.2017.09.008 VL - 119 SP - 99 EP - 117 ER - TY - GEN A1 - Duarte, Belmiro P.M. A1 - Sagnol, Guillaume A1 - Oliveira, Nuno M.C. T1 - A robust minimax Semidefinite Programming formulation for optimal design of experiments for model parametrization N2 - Model-based optimal design of experiments (M-bODE) is a crucial step in model parametrization since it encloses a framework that maximizes the amount of information extracted from a battery of lab experiments. We address the design of M-bODE for dynamic models considering a continuous representation of the design. We use Semidefinite Programming (SDP) to derive robust minmax formulations for nonlinear models, and extend the formulations to other criteria. The approaches are demonstrated for a CSTR where a two-step reaction occurs. T3 - ZIB-Report - 15-03 KW - Optimal design of experiments KW - Semidefinite Programming KW - Robust minmax designs Y1 - 2015 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:0297-zib-54626 SN - 1438-0064 ER - TY - GEN A1 - Sagnol, Guillaume T1 - A Class of Semidefinite Programs with rank-one solutions N2 - We show that a class of semidefinite programs (SDP) admits a solution that is a positive semidefinite matrix of rank at most $r$, where $r$ is the rank of the matrix involved in the objective function of the SDP. The optimization problems of this class are semidefinite packing problems, which are the SDP analogs to vector packing problems. Of particular interest is the case in which our result guarantees the existence of a solution of rank one: we show that the computation of this solution actually reduces to a Second Order Cone Program (SOCP). We point out an application in statistics, in the optimal design of experiments. T3 - ZIB-Report - 11-51 KW - SDP KW - Semidefinite Packing Problem KW - rank 1-solution KW - Low-rank solutions KW - SOCP KW - Optimal Experimental Design KW - Multiresponse experiments Y1 - 2012 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:0297-zib-14933 SN - 1438-0064 ER - TY - GEN A1 - Sagnol, Guillaume T1 - Network-related problems in Optimal Experimental Design and Second Order Cone Programming N2 - In the past few years several applications of optimal experimental designs have emerged to optimize the measurements in communication networks. The optimal design problems arising from this kind of applications share three interesting properties: (i) measurements are only available at a small number of locations of the network; (ii) each monitor can simultaneously measure several quantities, which can be modeled by ``multiresponse experiments"; (iii) the observation matrices depend on the topology of the network. In this paper, we give an overview of these experimental design problems and recall recent results for the computation of optimal designs by Second Order Cone Programming (SOCP). New results for the network-monitoring of a discrete time process are presented. In particular, we show that the optimal design problem for the monitoring of an AR1 process can be reduced to the standard form and we give experimental results. T3 - ZIB-Report - 11-52 KW - Optimal Experimental Design KW - Second Order Cone Programming KW - Network measurements Y1 - 2012 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:0297-zib-14942 SN - 1438-0064 VL - 51 IS - 51 SP - 161 EP - 171 ER - TY - GEN A1 - Harman, Radoslav A1 - Sagnol, Guillaume T1 - Computing D-optimal experimental designs for estimating treatment contrasts under the presence of a nuisance time trend N2 - We prove a mathematical programming characterisation of approximate partial D-optimality under general linear constraints. We use this characterisation with a branch-and-bound method to compute a list of all exact D-optimal designs for estimating a pair of treatment contrasts in the presence of a nuisance time trend up to the size of 24 consecutive trials. T3 - ZIB-Report - 15-02 KW - optimal design of experiments KW - nuisance trend KW - branch and bound Y1 - 2015 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:0297-zib-53640 SN - 1438-0064 ER - TY - CHAP A1 - Sagnol, Guillaume A1 - Harman, Radoslav ED - Steland, Ansgar ED - Rafajłowicz, Ewaryst ED - Szajowski, Krzysztof T1 - Optimal Designs for Steady-state Kalman filters T2 - Stochastic Models, Statistics and Their Applications N2 - We consider a stationary discrete-time linear process that can be observed by a finite number of sensors. The experimental design for the observations consists of an allocation of available resources to these sensors. We formalize the problem of selecting a design that maximizes the information matrix of the steady-state of the Kalman filter, with respect to a standard optimality criterion, such as $D-$ or $A-$optimality. This problem generalizes the optimal experimental design problem for a linear regression model with a finite design space and uncorrelated errors. Finally, we show that under natural assumptions, a steady-state optimal design can be computed by semidefinite programming. Y1 - 2015 U6 - https://doi.org/10.1007/978-3-319-13881-7_17 VL - 122 SP - 149 EP - 157 PB - Springer ER - TY - CHAP A1 - Harman, Radoslav A1 - Sagnol, Guillaume ED - Steland, Ansgar ED - Rafajłowicz, Ewaryst ED - Szajowski, Krzysztof T1 - Computing D-optimal experimental designs for estimating treatment contrasts under the presence of a nuisance time trend T2 - Stochastic Models, Statistics and Their Applications N2 - We prove a mathematical programming characterisation of approximate partial D-optimality under general linear constraints. We use this characterisation with a branch-and-bound method to compute a list of all exact D-optimal designs for estimating a pair of treatment contrasts in the presence of a nuisance time trend up to the size of 24 consecutive trials. Y1 - 2015 U6 - https://doi.org/10.1007/978-3-319-13881-7_10 VL - 122 SP - 83 EP - 91 PB - Springer ER - TY - GEN A1 - Sagnol, Guillaume A1 - Harman, Radoslav T1 - Optimal Designs for Steady-state Kalman filters N2 - We consider a stationary discrete-time linear process that can be observed by a finite number of sensors. The experimental design for the observations consists of an allocation of available resources to these sensors. We formalize the problem of selecting a design that maximizes the information matrix of the steady-state of the Kalman filter, with respect to a standard optimality criterion, such as $D-$ or $A-$optimality. This problem generalizes the optimal experimental design problem for a linear regression model with a finite design space and uncorrelated errors. Finally, we show that under natural assumptions, a steady-state optimal design can be computed by semidefinite programming. T3 - ZIB-Report - 14-39 KW - Optimal Design KW - Kalman Filter KW - Semidefinite programming Y1 - 2014 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:0297-zib-52808 SN - 1438-0064 ER - TY - JOUR A1 - Pronzato, Luc A1 - Sagnol, Guillaume T1 - Removing inessential points in c- and A-optimal design JF - Journal of Statistical Planning and Inference N2 - A design point is inessential when it does not contribute to an optimal design, and can therefore be safely discarded from the design space. We derive three inequalities for the detection of such inessential points in c-optimal design: the first two are direct consequences of the equivalence theorem for c-optimality; the third one is derived from a second-order cone programming formulation of c-optimal design. Elimination rules for A-optimal design are obtained as a byproduct. When implemented within an optimization algorithm, each inequality gives a screening test that may provide a substantial acceleration by reducing the size of the problem online. Several examples are presented with a multiplicative algorithm to illustrate the effectiveness of the approach. Y1 - 2021 UR - https://hal.archives-ouvertes.fr/hal-02868664 U6 - https://doi.org/10.1016/j.jspi.2020.11.011 VL - 213 SP - 233 EP - 252 ER -