32 citations · 87 across the 30 of their papers we have counts for
32 papers
Extrapolation-based Direct Search for Nonsmooth Stochastic Zeroth-Order Optimization
Anthony Palmieri, Francesco Rinaldi, Sara Shashaani
We propose and analyze a stochastic direct-search method for unconstrained zeroth-order minimization of locally Lipschitz, possibly nonsmooth, objectives. The method combines rando…
Relax and penalize: a new bilevel approach to mixed-binary hyperparameter optimization
Sara Venturini, Marianna de Santis, Jordan Patracone +3
In recent years, bilevel approaches have become very popular to efficiently estimate high-dimensional hyperparameters of machine learning models. However, to date, binary parameter…
Inexact Direct-Search Methods for Bilevel Optimization Problems
Youssef Diouane, Vyacheslav Kungurtsev, Francesco Rinaldi +1
In this work, we introduce new direct search schemes for the solution of bilevel optimization (BO) problems. Our methods rely on a fixed accuracy black box oracle for the lower-lev…
Learning the Right Layers: a Data-Driven Layer-Aggregation Strategy for Semi-Supervised Learning on Multilayer Graphs
Sara Venturini, Andrea Cristofari, Francesco Rinaldi +1
Clustering (or community detection) on multilayer graphs poses several additional complications with respect to standard graphs as different layers may be characterized by differen…
Projection free methods on product domains
Immanuel Bomze, Francesco Rinaldi, Damiano Zeffiro
Projection-free block-coordinate methods avoid high computational cost per iteration and at the same time exploit the particular problem structure of product domains. Frank-Wolfe-l…
Laplacian-based Semi-Supervised Learning in Multilayer Hypergraphs by Coordinate Descent
Sara Venturini, Andrea Cristofari, Francesco Rinaldi +1
Graph Semi-Supervised learning is an important data analysis tool, where given a graph and a set of labeled nodes, the aim is to infer the labels to the remaining unlabeled nodes.…
Retraction based Direct Search Methods for Derivative Free Riemannian Optimization
Vyacheslav Kungurtsev, Francesco Rinaldi, Damiano Zeffiro
Direct search methods represent a robust and reliable class of algorithms for solving black-box optimization problems. In this paper, we explore the application of those strategies…
Stochastic trust-region and direct-search methods: A weak tail bound condition and reduced sample sizing
Francesco Rinaldi, Luis Nunes Vicente, Damiano Zeffiro
Using tail bounds, we introduce a new probabilistic condition for function estimation in stochastic derivative-free optimization which leads to a reduction in the number of samples…
An oracle-based framework for robust combinatorial optimization
Enrico Bettiol, Christoph Buchheim, Marianna De Santis +1
We propose a general solution approach for min-max-robust counterparts of combinatorial optimization problems with uncertain linear objectives. We focus on the discrete scenario ca…
An Improved Penalty Algorithm using Model Order Reduction for MIPDECO problems with partial observations
Dominik Garmatter, Margherita Porcelli, Francesco Rinaldi +1
This work addresses optimal control problems governed by a linear time-dependent partial differential equation (PDE) as well as integer constraints on the control. Moreover, partia…
Minimization over the l1-ball using an active-set non-monotone projected gradient
Andrea Cristofari, Marianna De Santis, Stefano Lucidi +1
The l1-ball is a nicely structured feasible set that is widely used in many fields (e.g., machine learning, statistics and signal analysis) to enforce some sparsity in the model so…
Derivative-free methods for mixed-integer nonsmooth constrained optimization
Tommaso Giovannelli, Giampaolo Liuzzi, Stefano Lucidi +1
In this paper, we consider mixed-integer nonsmooth constrained optimization problems whose objective/constraint functions are available only as the output of a black-box zeroth-ord…
Frank-Wolfe and friends: a journey into projection-free first-order optimization methods
Immanuel. M. Bomze, Francesco Rinaldi, Damiano Zeffiro
Invented some 65 years ago in a seminal paper by Marguerite Straus-Frank and Philip Wolfe, the Frank-Wolfe method recently enjoys a remarkable revival, fuelled by the need of fast…
A Variance-aware Multiobjective Louvain-like Method for Community Detection in Multiplex Networks
Sara Venturini, Andrea Cristofari, Francesco Rinaldi +1
In this paper, we focus on the community detection problem in multiplex networks, i.e., networks with multiple layers having same node sets and no inter-layer connections. In parti…
A Unifying Framework for Sparsity Constrained Optimization
M. Lapucci, T. Levato, F. Rinaldi +1
In this paper, we consider the optimization problem of minimizing a continuously differentiable function subject to both convex constraints and sparsity constraints. By exploiting…
Fast cluster detection in networks by first-order optimization
Immanuel M. Bomze, Francesco Rinaldi, Damiano Zeffiro
Cluster detection plays a fundamental role in the analysis of data. In this paper, we focus on the use of s-defective clique models for network-based cluster detection and propose…
Avoiding bad steps in Frank Wolfe variants
Francesco Rinaldi, Damiano Zeffiro
The analysis of Frank Wolfe (FW) variants is often complicated by the presence of different kinds of "good" and "bad" steps. In this article we aim to simplify the convergence anal…
A unifying framework for the analysis of projection-free first-order methods under a sufficient slope condition
Francesco Rinaldi, Damiano Zeffiro
The analysis of projection-free first order methods is often complicated by the presence of different kinds of "good" and "bad" steps. In this article, we propose a unifying framew…
A derivative-free method for structured optimization problems
Andrea Cristofari, Francesco Rinaldi
Structured optimization problems are ubiquitous in fields like data science and engineering. The goal in structured optimization is using a prescribed set of points, called atoms,…
Solving non-monotone equilibrium problems via a DIRECT-type approach
Stefano Lucidi, Mauro Passacantando, Francesco Rinaldi
A global optimization approach for solving non-monotone equilibrium problems (EPs) is proposed. The class of (regularized) gap functions is used to reformulate any EP as a constrai…
Zero Order Stochastic Weakly Convex Composite Optimization
V. Kungurtsev, F. Rinaldi
In this paper we consider stochastic weakly convex composite problems, however without the existence of a stochastic subgradient oracle. We present a derivative free algorithm that…
Active set complexity of the Away-step Frank-Wolfe Algorithm
Immanuel M. Bomze, Francesco Rinaldi, Damiano Zeffiro
In this paper, we study active set identification results for the away-step Frank-Wolfe algorithm in different settings. We first prove a local identification property that we appl…
Total variation based community detection using a nonlinear optimization approach
Andrea Cristofari, Francesco Rinaldi, Francesco Tudisco
Maximizing the modularity of a network is a successful tool to identify an important community of nodes. However, this combinatorial optimization problem is known to be NP-complete…
Improved penalty algorithm for Mixed Integer PDE Constrained Optimization Problems
Dominik Garmatter, Margherita Porcelli, Francesco Rinaldi +1
Optimal control problems including partial differential equation (PDE) as well as integer constraints merge the combinatorial difficulties of integer programming and the challenges…