Francesco Rinaldi
YOU?
Author Swipe
View article: Probabilistic iterative hard thresholding for sparse learning
Probabilistic iterative hard thresholding for sparse learning Open
For statistical modeling wherein the data regime is unfavorable in terms of dimensionality relative to the sample size, finding hidden sparsity in the relationship structure between variables can be critical in formulating an accurate stat…
View article: An Efficient Network-aware Direct Search Method for Influence Maximization
An Efficient Network-aware Direct Search Method for Influence Maximization Open
Influence Maximization (IM) is a pivotal concept in social network analysis, involving the identification of influential nodes within a network to maximize the number of influenced nodes, and has a wide variety of applications that range f…
View article: Update Your Transformer to the Latest Release: Re-Basin of Task Vectors
Update Your Transformer to the Latest Release: Re-Basin of Task Vectors Open
Foundation models serve as the backbone for numerous specialized models developed through fine-tuning. However, when the underlying pretrained model is updated or retrained (e.g., on larger and more curated datasets), the fine-tuned model …
View article: Direct-search methods in the year 2025: Theoretical guarantees and algorithmic paradigms
Direct-search methods in the year 2025: Theoretical guarantees and algorithmic paradigms Open
International audience
View article: Frank–Wolfe and friends: a journey into projection-free first-order optimization methods
Frank–Wolfe and friends: a journey into projection-free first-order optimization methods Open
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 and reliable first-order optimization methods in Data Scien…
View article: What we should learn from pandemic publishing
What we should learn from pandemic publishing Open
View article: Probabilistic Iterative Hard Thresholding for Sparse Learning
Probabilistic Iterative Hard Thresholding for Sparse Learning Open
For statistical modeling wherein the data regime is unfavorable in terms of dimensionality relative to the sample size, finding hidden sparsity in the ground truth can be critical in formulating an accurate statistical model. The so-called…
View article: Projection free methods on product domains
Projection free methods on product domains Open
View article: Inexact direct-search methods for bilevel optimization problems
Inexact direct-search methods for bilevel optimization problems Open
View article: Direct-search methods in the year 2025: Theoretical guarantees and algorithmic paradigms
Direct-search methods in the year 2025: Theoretical guarantees and algorithmic paradigms Open
Optimizing a function without using derivatives is a challenging paradigm, that precludes from using classical algorithms from nonlinear optimization, and may thus seem intractable other than by using heuristics. Nevertheless, the field of…
View article: A machine learning approach for early identification of patients with severe imported malaria
A machine learning approach for early identification of patients with severe imported malaria Open
Background The aim of this study is to design ad hoc malaria learning (ML) approaches to predict clinical outcome in all patients with imported malaria and, therefore, to identify the best clinical setting. Methods This is a single-centre …
View article: Collaboration and topic switches in science
Collaboration and topic switches in science Open
View article: A Unifying Framework for Sparsity-Constrained Optimization
A Unifying Framework for Sparsity-Constrained Optimization Open
In this paper, we consider the optimization problem of minimizing a continuously differentiable function subject to both convex constraints and sparsity constraints. By exploiting a mixed-integer reformulation from the literature, we defin…
View article: Relax and penalize: a new bilevel approach to mixed-binary hyperparameter optimization
Relax and penalize: a new bilevel approach to mixed-binary hyperparameter optimization Open
In recent years, bilevel approaches have become very popular to efficiently estimate high-dimensional hyperparameters of machine learning models. However, to date, binary parameters are handled by continuous relaxation and rounding strateg…
View article: Relax and penalize: a new bilevel approach to mixed-binary hyperparameter optimization
Relax and penalize: a new bilevel approach to mixed-binary hyperparameter optimization Open
In recent years, bilevel approaches have become very popular to efficiently estimate high-dimensional hyperparameters of machine learning models. However, to date, binary parameters are handled by continuous relaxation and rounding strateg…
View article: Retraction-Based Direct Search Methods for Derivative Free Riemannian Optimization
Retraction-Based Direct Search Methods for Derivative Free Riemannian Optimization Open
Direct search methods represent a robust and reliable class of algorithms for solving black-box optimization problems. In this paper, the application of those strategies is exported to Riemannian optimization, wherein minimization is to be…
View article: Inexact Direct-Search Methods for Bilevel Optimization Problems
Inexact Direct-Search Methods for Bilevel Optimization Problems Open
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-level problem, and deal both with smooth and potentially nonsm…
View article: Learning the Right Layers: a Data-Driven Layer-Aggregation Strategy for Semi-Supervised Learning on Multilayer Graphs
Learning the Right Layers: a Data-Driven Layer-Aggregation Strategy for Semi-Supervised Learning on Multilayer Graphs Open
Clustering (or community detection) on multilayer graphs poses several additional complications with respect to standard graphs as different layers may be characterized by different structures and types of information. One of the major cha…
View article: OpenAlex slices for "Collaboration and topic switches in Science"
OpenAlex slices for "Collaboration and topic switches in Science" Open
OpenAlex slices stored as zipped parquet files. Needs pandas >= 2, pyarrow >= 7.
View article: Projection free methods on product domains
Projection free methods on product domains Open
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-like approaches rank among the most popular ones of this typ…
View article: Laplacian-based Semi-Supervised Learning in Multilayer Hypergraphs by Coordinate Descent
Laplacian-based Semi-Supervised Learning in Multilayer Hypergraphs by Coordinate Descent Open
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. In this paper, we start by considering an optimization-base…
View article: An oracle-based framework for robust combinatorial optimization
An oracle-based framework for robust combinatorial optimization Open
View article: Laplacian-based semi-Supervised learning in multilayer hypergraphs by coordinate descent
Laplacian-based semi-Supervised learning in multilayer hypergraphs by coordinate descent Open
View article: Minimization over the $$\ell _1$$-ball using an active-set non-monotone projected gradient
Minimization over the $$\ell _1$$-ball using an active-set non-monotone projected gradient Open
The $$\ell _1$$ -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 solutions. In this paper, we devise an active-set …
View article: An improved penalty algorithm using model order reduction for MIPDECO problems with partial observations
An improved penalty algorithm using model order reduction for MIPDECO problems with partial observations Open
View article: Derivative-free methods for mixed-integer nonsmooth constrained optimization
Derivative-free methods for mixed-integer nonsmooth constrained optimization Open
In this paper, mixed-integer nonsmooth constrained optimization problems are considered, where objective/constraint functions are available only as the output of a black-box zeroth-order oracle that does not provide derivative information.…
View article: Fast Cluster Detection in Networks by First Order Optimization
Fast Cluster Detection in Networks by First Order Optimization Open
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 a nonlinear optimization approach that efficiently handles …
View article: Retraction based Direct Search Methods for Derivative Free Riemannian Optimization
Retraction based Direct Search Methods for Derivative Free Riemannian Optimization Open
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 to Riemannian optimization, wherein minimization is to be …
View article: Stochastic trust-region and direct-search methods: A weak tail bound condition and reduced sample sizing
Stochastic trust-region and direct-search methods: A weak tail bound condition and reduced sample sizing Open
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 and eases algorithmic analyses. Moreover, we develop simpl…
View article: Mining for diamonds—Matrix generation algorithms for binary quadratically constrained quadratic problems
Mining for diamonds—Matrix generation algorithms for binary quadratically constrained quadratic problems Open