arXiv subjects

Marco Cococcioni

Publications and source records attributed to Marco Cococcioni.

8 recordsLinked to original sources

arXiv2026

PairedGTA: Generating Driving Datasets for Controlled Photometric Shift Analysis

Evaluating the performance of visual perception systems for autonomous driving is essential to ensure reliable operation across diverse environmental scenarios. Ideally, a balanced and fair analysis across different adverse conditions would require perfectly paired images of the same scene under different weather or illumination changes. This would allow evaluating the effect of photometric shifts independently of geometry and semantic changes. Unfortunately, real-world datasets rarely provide images of the same scene under different environmental conditions, because, normally, camera pose, traffic, and locations of dynamic objects (vehicles, pedestrians, etc.) vary over time, thus yielding only coarsely paired data. To address this challenge, this work introduces a data generation framework based on a high-fidelity game engine for extracting perfectly paired images. By leveraging software APIs that communicate with the GTA game engine, the framework modifies illumination and weather conditions while preserving scene geometry, camera pose, and the identity and placement of dynamic objects. For each sampled location, it procedurally instantiates dynamic entities and renders pixel-aligned images under diverse adverse conditions. The benefit of the proposed generation framework in driving scenarios is demonstrated through a systematic analysis of semantic segmentation models, whose output degradation can be attributed more directly to photometric shifts rather than to uncontrolled semantic or geometric factors.

cs.CV↗

arXiv2025

Microscaling Floating Point Formats for Large Language Models

The increasing computational and memory demands of large language models (LLMs) necessitate innovative approaches to optimize resource usage without compromising performance. This paper leverages microscaling floating-point formats, a novel technique designed to address these challenges by reducing the storage and computational overhead associated with numerical representations in LLMs. Unlike traditional floating-point representations that allocate a dedicated scale for each value, microscaling employs a shared scale across a block of values, enabling compact one-byte floating-point representations while maintaining an extended dynamic range. We explore the application of microscaling in the context of 8-bit floating-point formats to significantly reduce memory footprint and computational costs. We tested several configurations of microscaling floats within the GPT-2 LLM architecture, demonstrating that microscaling data formats can achieve competitive accuracy during training and inference, proving its efficacy as a resource-efficient alternative for deploying LLMs at scale. The source code is publicly available at: https://github.com/unipi-dii-compressedarith/llm.c-sve

cs.NE↗

arXiv2025

Solving Currency Arbitrage Problems using D-Wave Advantage2 Quantum Annealer

Quantum annealing has emerged as a powerful tool for solving combinatorial optimization problems efficiently, making use of the principles of quantum mechanics. Companies are increasingly investing in the market of quantum computers, providing the users with the possibility to solve these optimization problems by resorting to quantum computers. This paper explores how Quantum Annealing can be applied to the Currency Arbitrage (CA) optimization problem and its comparative performance against classical methods. A key contribution of the work is an original formulation of the CA problem as a QUBO (Quadratic Unconstrained Boolean Optimization) problem. We test the speed of D-wave quantum annealer, using the recently released latest version (Advantage 2).

quant-ph↗

arXiv2024

Informed deep hierarchical classification: a non-standard analysis inspired approach

This work proposes a novel approach to the deep hierarchical classification task, i.e., the problem of classifying data according to multiple labels organized in a rigid parent-child structure. It consists in a multi-output deep neural network equipped with specific projection operators placed before each output layer. The design of such an architecture, called lexicographic hybrid deep neural network (LH-DNN), has been possible by combining tools from different and quite distant research fields: lexicographic multi-objective optimization, non-standard analysis, and deep learning. To assess the efficacy of the approach, the resulting network is compared against the B-CNN, a convolutional neural network tailored for hierarchical classification tasks, on the CIFAR10, CIFAR100 (where it has been originally and recently proposed before being adopted and tuned for multiple real-world applications) and Fashion-MNIST benchmarks. Evidence states that an LH-DNN can achieve comparable if not superior performance, especially in the learning of the hierarchical relations, in the face of a drastic reduction of the learning parameters, training epochs, and computational time, without the need for ad-hoc loss functions weighting values.

cs.AI↗

arXiv2024

A Non-Archimedean Interior Point Method for Solving Lexicographic Multi-Objective Quadratic Programming Problems

This work presents a generalized implementation of the infeasible primal-dual Interior Point Method (IPM) achieved by the use of non-Archimedean values, i.e., infinite and infinitesimal numbers. The extended version, called here non-Archimedean IPM (NA-IPM), is proved to converge in polynomial time to a global optimum and to be able to manage infeasibility and unboundedness transparently, i.e., without considering them as corner cases: by means of a mild embedding (addition of two variables and one constraint) NA-IPM implicitly and transparently manages their possible presence. Moreover, the new algorithm is able to solve a wider variety of linear and quadratic optimization problems than its standard counterpart. Among them, the lexicographic multi-objective one deserves particular attention, since NA-IPM overcomes the issues that standard techniques (such as scalarization or preemptive approach) have. To support the theoretical properties of NA-IPM, the manuscript also shows four linear and quadratic non-Archimedean programming test cases where the effectiveness of the algorithm is verified. This also stresses that NA-IPM is not just a mere symbolic or theoretical algorithm but actually a concrete numerical tool, paving the way for its use in real-world problems in the near future.

math.OC↗

arXiv2024

PPU: Design and Implementation of a Pipelined Full Posit Processing Unit

By exploiting the modular RISC-V ISA this paper presents the customization of instruction set with posit\textsuperscript{\texttrademark} arithmetic instructions to provide improved numerical accuracy, well-defined behavior and increased range of representable numbers while keeping the flexibility and benefits of open-source ISA, like no licensing and royalty fee and community development. In this work we present the design, implementation and integration into the low-power Ibex RISC-V core of a full posit processing unit capable to directly implement in hardware the four arithmetic operations (add, sub, mul, div and fma), the inversion, the float-to-posit and posit-to-float conversions. We evaluate speed, power and area of this unit (that we have called Full Posit Processing Unit). The FPPU has been prototyped on Alveo and Kintex FPGAs, and its impact on the metrics of the full-RISC-V core have been evaluated, showing that we can provide real number processing capabilities to the mentioned core with an increase in area limited to $7\%$ for 8-bit posits and to $15\%$ for 16-bit posits. Finally we present tests one the use of posits for deep neural networks with different network models and datasets, showing minimal drop in accuracy when using 16-bit posits instead of 32-bit IEEE floats.

cs.AR↗

arXiv2023

Compressed Real Numbers for AI: a case-study using a RISC-V CPU

As recently demonstrated, Deep Neural Networks (DNN), usually trained using single precision IEEE 754 floating point numbers (binary32), can also work using lower precision. Therefore, 16-bit and 8-bit compressed format have attracted considerable attention. In this paper, we focused on two families of formats that have already achieved interesting results in compressing binary32 numbers in machine learning applications, without sensible degradation of the accuracy: bfloat and posit. Even if 16-bit and 8-bit bfloat/posit are routinely used for reducing the storage of the weights/biases of trained DNNs, the inference still often happens on the 32-bit FPU of the CPU (especially if GPUs are not available). In this paper we propose a way to decompress a tensor of bfloat/posits just before computations, i.e., after the compressed operands have been loaded within the vector registers of a vector capable CPU, in order to save bandwidth usage and increase cache efficiency. Finally, we show the architectural parameters and considerations under which this solution is advantageous with respect to the uncompressed one.

cs.LG↗

arXiv2020

Numerical Asymptotic Results in Game Theory Using Sergeyev's Infinity Computing

Prisoner's Dilemma (PD) is a widely studied game that plays an important role in Game Theory. This paper aims at extending PD Tournaments to the case of infinite, finite or infinitesimal payoffs using Sergeyev's Infinity Computing (IC). By exploiting IC, we are able to show the limits of the classical approach to PD Tournaments analysis of the classical theory, extending both the sets of the feasible and numerically computable tournaments. In particular we provide a numerical computation of the exact outcome of a simple PD Tournament where one player meets every other an infinite number of times, for both its deterministic and stochastic formulations.

cs.GT↗