We propose an inexact proximal augmented Lagrangian method (P-ALM) for nonconvex structured optimization problems. The proposed method features an easily implementable rule not only for updating the penalty parameters, but also for adaptively tuning the proximal term. It allows the penalty parameter to grow rapidly in the early stages to speed up progress, while ameliorating the issue of ill-conditioning in later iterations, a well-known drawback of the traditional approach of linearly increasing the penalty parameters. A key element in our analysis lies in the observation that the augmented Lagrangian can be controlled effectively along the iterates, provided an initial feasible point is available. Our analysis, while simple, provides a new theoretical perspective about P-ALM and, as a by-product, results in similar convergence properties for its non-proximal variant, the classical augmented Lagrangian method (ALM). Numerical experiments, including convex and nonconvex problem instances, demonstrate the effectiveness of our approach.

Policy as Code (PaC) is a paradigm that encodes security and compliance policies into machine-readable formats, enabling automated enforcement in Infrastructure as Code (IaC) environments. However, its adoption is hindered by the complexity of policy languages and the risk of misconfigurations. In this work, we present ARPaCCino, an agentic system that combines Large Language Models (LLMs), Retrieval-Augmented-Generation (RAG), and tool-based validation to automate the generation and verification of PaC rules. Given natural language descriptions of the desired policies, ARPaCCino generates formal Rego rules, assesses IaC compliance, and iteratively refines the IaC configurations to ensure conformance. Thanks to its modular agentic architecture and integration with external tools and knowledge bases, ARPaCCino supports policy validation across a wide range of technologies, including niche or emerging IaC frameworks. Experimental evaluation involving a Terraform-based case study demonstrates ARPaCCino's effectiveness in generating syntactically and semantically correct policies, identifying non-compliant infrastructures, and applying corrective modifications, even when using smaller, open-weight LLMs. Our results highlight the potential of agentic RAG architectures to enhance the automation, reliability, and accessibility of PaC workflows.

Audio deepfakes represent a growing threat to digital security and trust, leveraging advanced generative models to produce synthetic speech that closely mimics real human voices. Detecting such manipulations is especially challenging under open-world conditions, where spoofing methods encountered during testing may differ from those seen during training. In this work, we propose an end-to-end deep learning framework for audio deepfake detection that operates directly on raw waveforms. Our model, RawNetLite, is a lightweight convolutional-recurrent architecture designed to capture both spectral and temporal features without handcrafted preprocessing. To enhance robustness, we introduce a training strategy that combines data from multiple domains and adopts Focal Loss to emphasize difficult or ambiguous samples. We further demonstrate that incorporating codec-based manipulations and applying waveform-level audio augmentations (e.g., pitch shifting, noise, and time stretching) leads to significant generalization improvements under realistic acoustic conditions. The proposed model achieves over 99.7% F1 and 0.25% EER on in-domain data (FakeOrReal), and up to 83.4% F1 with 16.4% EER on a challenging out-of-distribution test set (AVSpoof2021 + CodecFake). These findings highlight the importance of diverse training data, tailored objective functions and audio augmentations in building resilient and generalizable audio forgery detectors. Code and pretrained models are available at this https URL

We study data-driven least squares (LS) problems with semidefinite (SD) constraints and derive finite-sample guarantees on the spectrum of their optimal solutions when these constraints are relaxed. In particular, we provide a high confidence bound allowing one to solve a simpler program in place of the full SDLS problem, while ensuring that the eigenvalues of the resulting solution are $\varepsilon$-close of those enforced by the SD constraints. The developed certificate, which consistently shrinks as the number of data increases, turns out to be easy-to-compute, distribution-free, and only requires independent and identically distributed samples. Moreover, when the SDLS is used to learn an unknown quadratic function, we establish bounds on the error between a gradient descent iterate minimizing the surrogate cost obtained with no SD constraints and the true minimizer.

We propose ZeroFPR, a nonmonotone linesearch algorithm for minimizing the sum of two nonconvex functions, one of which is smooth and the other possibly nonsmooth. ZeroFPR is the first algorithm that, despite being fit for fully nonconvex problems and requiring only the black-box oracle of forward-backward splitting (FBS) --- namely evaluations of the gradient of the smooth term and of the proximity operator of the nonsmooth one --- achieves superlinear convergence rates under mild assumptions at the limit point when the linesearch directions satisfy a Dennis-Mor\'e condition, and we show that this is the case for quasi-Newton directions. Our approach is based on the forward-backward envelope (FBE), an exact and strictly continuous penalty function for the original cost. Extending previous results we show that, despite being nonsmooth for fully nonconvex problems, the FBE still enjoys favorable first- and second-order properties which are key for the convergence results of ZeroFPR. Our theoretical results are backed up by promising numerical simulations. On large-scale problems, by computing linesearch directions using limited-memory quasi-Newton updates our algorithm greatly outperforms FBS and its accelerated variant (AFBS).

We present EGN, a stochastic second-order optimization algorithm that combines the generalized Gauss-Newton (GN) Hessian approximation with low-rank linear algebra to compute the descent direction. Leveraging the Duncan-Guttman matrix identity, the parameter update is obtained by factorizing a matrix which has the size of the mini-batch. This is particularly advantageous for large-scale machine learning problems where the dimension of the neural network parameter vector is several orders of magnitude larger than the batch size. Additionally, we show how improvements such as line search, adaptive regularization, and momentum can be seamlessly added to EGN to further accelerate the algorithm. Moreover, under mild assumptions, we prove that our algorithm converges to an $\epsilon$-stationary point at a linear rate. Finally, our numerical experiments demonstrate that EGN consistently exceeds, or at most matches the generalization performance of well-tuned SGD, Adam, and SGN optimizers across various supervised and reinforcement learning tasks.

Control Invariant (CI) sets are instrumental in certifying the safety of dynamical systems. Control Barrier Functions (CBFs) are effective tools to compute such sets, since the zero sublevel sets of CBFs are CI sets. However, computing CBFs generally involves addressing a complex robust optimization problem, which can be intractable. Scenario-based methods have been proposed to simplify this computation. Then, one needs to verify if the CBF actually satisfies the robust constraints. We present an approach to perform this verification that relies on Lipschitz arguments, and forms the basis of a certification algorithm designed for sample efficiency. Through a numerical example, we validated the efficiency of the proposed procedure.

We design specific neural networks (NNs) for the identification of switching nonlinear systems in the state-space form, which explicitly model the switching behavior and address the inherent coupling between system parameters and switching modes. This coupling is specifically addressed by leveraging the expectation-maximization (EM) framework. In particular, our technique will combine a moving window approach in the E-step to efficiently estimate the switching sequence, together with an extended Kalman filter (EKF) in the M-step to train the NNs with a quadratic convergence rate. Extensive numerical simulations, involving both academic examples and a battery charge management system case study, illustrate that our technique outperforms available ones in terms of parameter estimation accuracy, model fitting, and switching sequence identification.

Reinforcement Learning (RL) is a powerful tool to perform data-driven optimal control without relying on a model of the system. However, RL struggles to provide hard guarantees on the behavior of the resulting control scheme. In contrast, Nonlinear Model Predictive Control (NMPC) and Economic NMPC (ENMPC) are standard tools for the closed-loop optimal control of complex systems with constraints and limitations, and benefit from a rich theory to assess their closed-loop behavior. Unfortunately, the performance of (E)NMPC hinges on the quality of the model underlying the control scheme. In this paper, we show that an (E)NMPC scheme can be tuned to deliver the optimal policy of the real system even when using a wrong model. This result also holds for real systems having stochastic dynamics. This entails that ENMPC can be used as a new type of function approximator within RL. Furthermore, we investigate our results in the context of ENMPC and formally connect them to the concept of dissipativity, which is central for the ENMPC stability. Finally, we detail how these results can be used to deploy classic RL tools for tuning (E)NMPC schemes. We apply these tools on both a classical linear MPC setting and a standard nonlinear example from the ENMPC literature.

Deep learning has bolstered gaze estimation techniques, but real-world deployment has been impeded by inadequate training datasets. This problem is exacerbated by both hardware-induced variations in eye images and inherent biological differences across the recorded participants, leading to both feature and pixel-level variance that hinders the generalizability of models trained on specific datasets. While synthetic datasets can be a solution, their creation is both time and resource-intensive. To address this problem, we present a framework called Light Eyes or "LEyes" which, unlike conventional photorealistic methods, only models key image features required for video-based eye tracking using simple light distributions. LEyes facilitates easy configuration for training neural networks across diverse gaze-estimation tasks. We demonstrate that models trained using LEyes are consistently on-par or outperform other state-of-the-art algorithms in terms of pupil and CR localization across well-known datasets. In addition, a LEyes trained model outperforms the industry standard eye tracker using significantly more cost-effective hardware. Going forward, we are confident that LEyes will revolutionize synthetic data generation for gaze estimation models, and lead to significant improvements of the next generation video-based eye trackers.

In this study, we investigate the continuous time dynamics of Recurrent Neural Networks (RNNs), focusing on systems with nonlinear activation functions. The objective of this work is to identify conditions under which RNNs exhibit perpetual oscillatory behavior, without converging to static fixed points. We establish that skew-symmetric weight matrices are fundamental to enable stable limit cycles in both linear and nonlinear configurations. We further demonstrate that hyperbolic tangent-like activation functions (odd, bounded, and continuous) preserve these oscillatory dynamics by ensuring motion invariants in state space. Numerical simulations showcase how nonlinear activation functions not only maintain limit cycles, but also enhance the numerical stability of the system integration process, mitigating those instabilities that are commonly associated with the forward Euler method. The experimental results of this analysis highlight practical considerations for designing neural architectures capable of capturing complex temporal dependencies, i.e., strategies for enhancing memorization skills in recurrent models.

The communication channels used to convey information between the components of wireless networked control systems (WNCSs) are subject to packet losses due to time-varying fading and interference. We consider a wireless networked control scenario, where the packet loss occurs in both the sensor-controller link (sensing link) and the controller-actuator link (actuation link). Moreover, we consider one time-step delay mode observations of the actuation link. While the problems of state feedback optimal control and stabilizability conditions for systems with one time-step delay mode observations of the actuation link have been already solved, we study the optimal output feedback control problem, and we derive a separation principle for the aforementioned wireless networked control scenario. Particularly, we show that the optimal control problem (with one time-step delay in the mode observation of actuation link state) and the optimal filtering problem can be solved independently under a TCP-like communication scheme.

There has been an increasing focus in learning interpretable feature representations, particularly in applications such as medical image analysis that require explainability, whilst relying less on annotated data (since annotations can be tedious and costly). Here we build on recent innovations in style-content representations to learn anatomy, imaging characteristics (appearance) and temporal correlations. By introducing a self-supervised objective of predicting future cardiac phases we improve disentanglement. We propose a temporal transformer architecture that given an image conditioned on phase difference, it predicts a future frame. This forces the anatomical decomposition to be consistent with the temporal cardiac contraction in cine MRI and to have semantic meaning with less need for annotations. We demonstrate that using this regularization, we achieve competitive results and improve semi-supervised segmentation, especially when very few labelled data are available. Specifically, we show Dice increase of up to 19\% and 7\% compared to supervised and semi-supervised approaches respectively on the ACDC dataset. Code is available at: this https URL .

Covert channel networks are a well-known method for circumventing the security measures organizations put in place to protect their networks from adversarial attacks. This paper introduces a novel method based on bit-rate modulation for implementing covert channels between devices connected over a wide area network. This attack can be exploited to exfiltrate sensitive information from a machine (i.e., covert sender) and stealthily transfer it to a covert receiver while evading network security measures and detection systems. We explain how to implement this threat, focusing specifically on covert channel networks and their potential security risks to network information transmission. The proposed method leverages bit-rate modulation, where a high bit rate represents a '1' and a low bit rate represents a '0', enabling covert communication. We analyze the key metrics associated with covert channels, including robustness in the presence of legitimate traffic and other interference, bit-rate capacity, and bit error rate. Experiments demonstrate the good performance of this attack, which achieved 5 bps with excellent robustness and a channel capacity of up to 0.9239 bps/Hz under different noise sources. Therefore, we show that bit-rate modulation effectively violates network security and compromises sensitive data.

We analyze the economic and environmental impacts of the European Carbon Border Adjustment Mechanism (CBAM) using a multi-country, multi-sector general equilibrium model with input-output linkages. We quantify the general equilibrium responses of trade flows, welfare, and emissions. To our knowledge, we developed the first quantitative trade model that jointly endogenizes both the Emissions Trading System (ETS) allowance and the CBAM prices. We find that CBAM marginally increases EU Gross National Expenditure (GNE) and shifts trade toward more domestic and cleaner production. Emissions embodied in direct EU imports fall by 4.8%, and by 3% when including indirect emissions -- underscoring the importance of accounting for production networks in evaluating policy outcomes.

This paper introduces adaptive Bregman proximal gradient algorithms for solving convex composite minimization problems without relying on global relative smoothness or strong convexity assumptions. Building upon recent advances in adaptive stepsize selections, the proposed methods generate stepsizes based on local curvature estimates, entirely eliminating the need for backtracking linesearch. A key innovation is a Bregman generalization of Young's inequality, which allows controlling a critical inner product in terms of the same Bregman distances used in the updates. Our theory applies to problems where the differentiable term is merely locally smooth relative to a distance-generating function, without requiring the existence of global moduli or symmetry coefficients. Numerical experiments demonstrate their competitive performance compared to existing approaches across various problem classes.

We consider the problem of designing a machine learning-based model of an unknown dynamical system from a finite number of (state-input)-successor state data points, such that the model obtained is also suitable for optimal control design. We adopt a neural network (NN) architecture that, once suitably trained, yields a hybrid system with continuous piecewise-affine (PWA) dynamics that is differentiable with respect to the network's parameters, thereby enabling the use of derivative-based training procedures. We show that a careful choice of our NN's weights produces a hybrid system model with structural properties that are highly favorable when used as part of a finite horizon optimal control problem (OCP). Specifically, we rely on available results to establish that optimal solutions with strong local optimality guarantees can be computed via nonlinear programming (NLP), in contrast to classical OCPs for general hybrid systems which typically require mixed-integer optimization. Besides being well-suited for optimal control design, numerical simulations illustrate that our NN-based technique enjoys very similar performance to state-of-the-art system identification methods for hybrid systems and it is competitive on nonlinear benchmarks.

We present a general system identification procedure capable of estimating of a broad spectrum of state-space dynamical models, including linear time-invariant (LTI), linear parameter-varying} (LPV), and nonlinear (NL) dynamics, along with rather general classes of noise models. Similar to the LTI case, we show that for this general class of model structures, including the NL case, the model dynamics can be separated into a deterministic process and a stochastic noise part, allowing to seamlessly tune the complexity of the combined model both in terms of nonlinearity and noise modeling. We parameterize the involved nonlinear functional relations by means of artificial neural-networks (ANNs), although alternative parametric nonlinear mappings can also be used. To estimate the resulting model structures, we optimize a prediction-error-based criterion using an efficient combination of a constrained quasi-Newton approach and automatic differentiation, achieving training times in the order of seconds compared to existing state-of-the-art ANN methods which may require hours for models of similar complexity. We formally establish the consistency guarantees for the proposed approach and demonstrate its superior estimation accuracy and computational efficiency on several benchmark LTI, LPV, and NL system identification problems.