arXiv subjects

Lorenzo Lampariello

Publications and source records attributed to Lorenzo Lampariello.

9 recordsLinked to original sources

arXiv2024

Scalarization via utility functions in multi-objective optimization

We study a general scalarization approach via utility functions in multi-objective optimization. It consists of maximizing utility which is obtained from the objectives' bargaining with regard to a disagreement reference point. The theoretical framework for a broad class of utility functions from microeconomics is developed. For that, we associate a utility-dependent single-objective optimization problem with the given multi-objective optimization problem. We show that Pareto optimal points of the latter can be recovered by solving the former. In particular, Cobb-Douglas, Leontief, and CES utility functions are considered. We prove that any Pareto optimal point can be obtained as a solution of scalarization via one of the mentioned utility functions. Further, we propose a numerical scheme to solve utility-dependent single-objective optimization problems. Here, the main difficulty comes from the necessity to address constraints which are associated with a disagreement reference point. Our crucial observation is that the explicit treatment of these additional constraints may be avoided. This is the case if the Slater condition is satisfied and the utility function under consideration has the so-called barrier property. Under these assumptions, we prove the convergence of our scheme to Pareto optimal points. Numerical experiments on real-world financial datasets in a portfolio selection context confirm the efficiency of our scalarization approach via utility functions.

math.OC↗

arXiv2023

A new behavioral model for portfolio selection using the Half-Full/Half-Empty approach

We focus on a behavioral model, that has been recently proposed in the literature, whose rational can be traced back to the Half-Full/Half-Empty glass metaphor. More precisely, we generalize the Half-Full/Half-Empty approach to the context of positive and negative lotteries and give financial and behavioral interpretations of the Half-Full/Half-Empty parameters. We develop a portfolio selection model based on the Half-Full/Half-Empty strategy, resulting in a nonconvex optimization problem, which, nonetheless, is proven to be equivalent to an alternative Mixed-Integer Linear Programming formulation. By means of the ensuing empirical analysis, based on three real-world datasets, the Half-Full/Half-Empty model is shown to be very versatile by appropriately varying its parameters, and to provide portfolios displaying promising performances in terms of risk and profitability, compared with Prospect Theory, risk minimization approaches and Equally-Weighted portfolios.

q-fin.PM↗

arXiv2021

On the solution of monotone nested variational inequalities

We study nested variational inequalities, which are variational inequalities whose feasible set is the solution set of another variational inequality. We present a projected averaging Tikhonov algorithm requiring the weakest conditions in the literature to guarantee the convergence to solutions of the nested variational inequality. Specifically, we only need monotonicity of the upper- and the lower-level variational inequalities. Also, we provide the first complexity analysis for nested variational inequalities considering optimality of both the upper- and lower-level.

math.OC↗

arXiv2020

Diminishing Stepsize Methods for Nonconvex Composite Problems via Ghost Penalties: from the General to the Convex Regular Constrained Case

In this paper we first extend the diminishing stepsize method for nonconvex constrained problems presented in [4] to deal with equality constraints and a nonsmooth objective function of composite type. We then consider the particular case in which the constraints are convex and satisfy a standard constraint qualification and show that in this setting the algorithm can be considerably simplified, reducing the computational burden of each iteration.

math.OC↗

arXiv2020

Ghost Penalties in Nonconvex Constrained Optimization: Diminishing Stepsizes and Iteration Complexity

We consider nonconvex constrained optimization problems and propose a new approach to the convergence analysis based on penalty functions. We make use of classical penalty functions in an unconventional way, in that penalty functions only enter in the theoretical analysis of convergence while the algorithm itself is penalty-free. Based on this idea, we are able to establish several new results, including the first general analysis for diminishing stepsize methods in nonconvex, constrained optimization, showing convergence to generalized stationary points, and a complexity study for SQP-type algorithms.

math.OC↗

arXiv2018

A dominance maximization approach to portfolio selection

In the portfolio multiobjective optimization framework, we propose to compare and choose, among all feasible asset portfolios of a given market, the one that maximizes the product of the distances between its values of risk and gain and those of a suitable reference point (e.g., the so-called nadir). We show that this approach has distinctive and remarkable features. While being not influenced by how the objectives are scaled, it provides one with an efficient (Pareto) portfolio that "dominates the most" with respect to the reference point. Furthermore, although our no-preference strategy generally requires the solution of a nonconvex (constrained) single-objective problem, we show how the resulting (global) optimal portfolio can be easily and efficiently computed. We also perform numerical tests based on some publicly available benchmark data sets often used in the literature, highlighting the nice properties of our approach.

math.OC↗

arXiv2016

A Bridge between Bilevel Programs and Nash Games

We study connections between optimistic bilevel programming problems and Generalized Nash Equilibrium Problems (GNEP)s. We remark that, when addressing bilevel problems, we consider the general case in which the lower level program is not assumed to have a unique solution. Inspired by the optimal value approach, we propose a new GNEP model that is closely related to the bilevel program. We provide a complete analysis of the relationship between the "vertical" bilevel problem and the corresponding "horizontal" (one-level) GNEP model. We define classes of problems for which solutions of the bilevel program can be computed by finding equilibria of the GNEP. We develop a simple algorithm, which turns out to be globally convergent, for the solution of classes of our GNEP; we study how it is then possible to recover a solution of the bilevel problem from the computed equilibrium. Numerical experience shows the effectiveness of our approach, even when addressing big nonlinear bilevel problems.

math.OC↗

arXiv2016

Parallel and Distributed Methods for Nonconvex Optimization--Part II: Applications

In Part I of this paper, we proposed and analyzed a novel algorithmic framework for the minimization of a nonconvex (smooth) objective function, subject to nonconvex constraints, based on inner convex approximations. This Part II is devoted to the application of the framework to some resource allocation problems in communication networks. In particular, we consider two non-trivial case-study applications, namely: (generalizations of) i) the rate profile maximization in MIMO interference broadcast networks; and the ii) the max-min fair multicast multigroup beamforming problem in a multi-cell environment. We develop a new class of algorithms enjoying the following distinctive features: i) they are \emph{distributed} across the base stations (with limited signaling) and lead to subproblems whose solutions are computable in closed form; and ii) differently from current relaxation-based schemes (e.g., semidefinite relaxation), they are proved to always converge to d-stationary solutions of the aforementioned class of nonconvex problems. Numerical results show that the proposed (distributed) schemes achieve larger worst-case rates (resp. signal-to-noise interference ratios) than state-of-the-art centralized ones while having comparable computational complexity.

cs.IT↗

arXiv2016

Parallel and Distributed Methods for Nonconvex Optimization-Part I: Theory

In this two-part paper, we propose a general algorithmic framework for the minimization of a nonconvex smooth function subject to nonconvex smooth constraints. The algorithm solves a sequence of (separable) strongly convex problems and mantains feasibility at each iteration. Convergence to a stationary solution of the original nonconvex optimization is established. Our framework is very general and flexible; it unifies several existing Successive Convex Approximation (SCA)-based algorithms such as (proximal) gradient or Newton type methods, block coordinate (parallel) descent schemes, difference of convex functions methods, and improves on their convergence properties. More importantly, and differently from current SCA approaches, it naturally leads to distributed and parallelizable implementations for a large class of nonconvex problems. This Part I is devoted to the description of the framework in its generality. In Part II we customize our general methods to several multi-agent optimization problems, mainly in communications and networking; the result is a new class of (distributed) algorithms that compare favorably to existing ad-hoc (centralized) schemes (when they exist).

cs.MA↗