arXiv subjects

Andrea Pinto

Publications and source records attributed to Andrea Pinto.

8 recordsLinked to original sources

arXiv2026

Central Bank Digital Currencies: Where is the Privacy, Technology, and Anonymity?

In an age of financial system digitisation and the increasing adoption of digital currencies, Central Bank Digital Currencies (CBDCs) have emerged as a focal point for technological innovation. Privacy compliance has become a key factor in the successful design of CBDCs, extending beyond technical requirements to influence legal requirements, user trust, and security considerations. Implementing Privacy-Enhancing Technologies (PETs) in CBDCs requires an interdisciplinary approach, however, the lack of a common understanding of privacy and the essential technological characteristics restricts progress. This work investigates: (1) How privacy can be defined within the framework of CBDCs and what implications does this definition have for CBDCs design? and (2) Which PETs can be employed to enhance privacy in CBDC design? We propose a comprehensive definition for privacy that is mapped to the cryptographic landscape for feature implementation. The research is validated against case studies from 20 current CBDCs. The study shows that comprehensive privacy can be designed in the proposal stage, but that privacy does not reach the launched version of the CBDC. A failure analysis of abandoned privacy pilots identifies four root causes of this research-to-launch gap: regulatory visibility requirements, computational overhead, liability allocation, and institutional incentives.

cs.CR↗

arXiv2025

Additive decomposition of one-dimensional signals using Transformers

One-dimensional signal decomposition is a well-established and widely used technique across various scientific fields. It serves as a highly valuable pre-processing step for data analysis. While traditional decomposition techniques often rely on mathematical models, recent research suggests that applying the latest deep learning models to this problem presents an exciting, unexplored area with promising potential. This work presents a novel method for the additive decomposition of one-dimensional signals. We leverage the Transformer architecture to decompose signals into their constituent components: piece-wise constant, smooth (low-frequency oscillatory), textured (high-frequency oscillatory), and a noise component. Our model, trained on synthetic data, achieves excellent accuracy in modeling and decomposing input signals from the same distribution, as demonstrated by the experimental results.

cs.LG↗

arXiv2024

On Generalization Bounds for Neural Networks with Low Rank Layers

While previous optimization results have suggested that deep neural networks tend to favour low-rank weight matrices, the implications of this inductive bias on generalization bounds remain underexplored. In this paper, we apply Maurer's chain rule for Gaussian complexity to analyze how low-rank layers in deep networks can prevent the accumulation of rank and dimensionality factors that typically multiply across layers. This approach yields generalization bounds for rank and spectral norm constrained networks. We compare our results to prior generalization bounds for deep networks, highlighting how deep networks with low-rank layers can achieve better generalization than those with full-rank layers. Additionally, we discuss how this framework provides new perspectives on the generalization capabilities of deep networks exhibiting neural collapse.

cs.LG↗

arXiv2024

The Fair Language Model Paradox

Large Language Models (LLMs) are widely deployed in real-world applications, yet little is known about their training dynamics at the token level. Evaluation typically relies on aggregated training loss, measured at the batch level, which overlooks subtle per-token biases arising from (i) varying token-level dynamics and (ii) structural biases introduced by hyperparameters. While weight decay is commonly used to stabilize training, we reveal that it silently introduces performance biases detectable only at the token level. In fact, we empirically show across different dataset sizes, model architectures and sizes ranging from 270M to 3B parameters that as weight decay increases, low-frequency tokens are disproportionately depreciated. This is particularly concerning, as these neglected low-frequency tokens represent the vast majority of the token distribution in most languages, calling for novel regularization techniques that ensure fairness across all available tokens.

cs.CL↗

arXiv2024

How Neural Networks Learn the Support is an Implicit Regularization Effect of SGD

We investigate the ability of deep neural networks to identify the support of the target function. Our findings reveal that mini-batch SGD effectively learns the support in the first layer of the network by shrinking to zero the weights associated with irrelevant components of input. In contrast, we demonstrate that while vanilla GD also approximates the target function, it requires an explicit regularization term to learn the support in the first layer. We prove that this property of mini-batch SGD is due to a second-order implicit regularization effect which is proportional to $\eta / b$ (step size / batch size). Our results are not only another proof that implicit regularization has a significant impact on training optimization dynamics but they also shed light on the structure of the features that are learned by the network. Additionally, they suggest that smaller batches enhance feature interpretability and reduce dependency on initialization.

cs.LG↗

arXiv2024

The PEAL Method: a mathematical framework to streamline securitization structuring

Securitization is a financial process where the cash flows of income-generating assets are sold to institutional investors as securities, liquidating illiquid assets. This practice presents persistent challenges due to the absence of a comprehensive mathematical framework for structuring asset-backed securities. While existing literature provides technical analysis of credit risk modeling, there remains a need for a definitive framework detailing the allocation of the inbound cash flows to the outbound positions. To fill this gap, we introduce the PEAL Method: a 10-step mathematical framework to streamline the securitization structuring across all time periods. The PEAL Method offers a rigorous and versatile approach, allowing practitioners to structure various types of securitizations, including those with complex vertical positions. By employing standardized equations, it facilitates the delineation of payment priorities and enhances risk characterization for both the asset and the liability sides throughout the securitization life cycle. In addition to its technical contributions, the PEAL Method aims to elevate industry standards by addressing longstanding challenges in securitization. By providing detailed information to investors and enabling transparent risk profile comparisons, it promotes market transparency and enables stronger regulatory oversight. In summary, the PEAL Method represents a significant advancement in securitization literature, offering a standardized framework for precision and efficiency in structuring transactions. Its adoption has the potential to drive innovation and enhance risk management practices in the securitization market.

q-fin.RM↗

arXiv2023

Privacy and Efficiency of Communications in Federated Split Learning

Everyday, large amounts of sensitive data is distributed across mobile phones, wearable devices, and other sensors. Traditionally, these enormous datasets have been processed on a single system, with complex models being trained to make valuable predictions. Distributed machine learning techniques such as Federated and Split Learning have recently been developed to protect user data and privacy better while ensuring high performance. Both of these distributed learning architectures have advantages and disadvantages. In this paper, we examine these tradeoffs and suggest a new hybrid Federated Split Learning architecture that combines the efficiency and privacy benefits of both. Our evaluation demonstrates how our hybrid Federated Split Learning approach can lower the amount of processing power required by each client running a distributed learning system, reduce training and inference time while keeping a similar accuracy. We also discuss the resiliency of our approach to deep learning privacy inference attacks and compare our solution to other recently proposed benchmarks.

cs.LG↗

arXiv2022

The effectiveness of factorization and similarity blending

Collaborative Filtering (CF) is a widely used technique which allows to leverage past users' preferences data to identify behavioural patterns and exploit them to predict custom recommendations. In this work, we illustrate our review of different CF techniques in the context of the Computational Intelligence Lab (CIL) CF project at ETH Zürich. After evaluating the performances of the individual models, we show that blending factorization-based and similarity-based approaches can lead to a significant error decrease (-9.4%) on the best-performing stand-alone model. Moreover, we propose a novel stochastic extension of a similarity model, SCSR, which consistently reduce the asymptotic complexity of the original algorithm.

cs.IR↗