activity
20242026
most citedQuantifying Cryptocurrency Unpredictability: A Comprehensive Study of Complexity and Forecasting

6 citations · 17 across the 17 of their papers we have counts for

collaborators
Showing cs.LGShow all

15 papers · 1 filter

cs.LG2026

What changes after deployment? A survey on On-device Learning in TinyML

Massimo Pavan, Luca Pezzarossa, Fabrizio Pittorino +2

Machine learning models on microcontroller-class devices (TinyML) face a fundamental challenge: post-deployment distribution change undermines static models. On-device learning (OD…

cs.LG2026

HERCULES: Hardware-Efficient, Robust, Continual Learning Neural Architecture Search

Matteo Gambella, Fabrizio Pittorino, Manuel Roveri

Neural Architecture Search (NAS) has emerged as a powerful framework for automatically discovering neural architectures that balance accuracy and efficiency. However, as AI transit…

cs.LG2026

SQUAD: Scalable Quorum Adaptive Decisions via ensemble of early exit neural networks

Matteo Gambella, Fabrizio Pittorino, Giuliano Casale +1

Early-exit neural networks have become popular for reducing inference latency by allowing intermediate predictions when sufficient confidence is achieved. However, standard approac…

cs.LG2025

DQT: Dynamic Quantization Training via Dequantization-Free Nested Integer Arithmetic

Hazem Hesham Yousef Shalby, Fabrizio Pittorino, Francesca Palermo +2

The deployment of deep neural networks on resource-constrained devices relies on quantization. While static, uniform quantization applies a fixed bit-width to all inputs, it fails…

cs.LG2025

InfoQ: Mixed-Precision Quantization via Global Information Flow

Mehmet Emre Akbulut, Hazem Hesham Yousef Shalby, Fabrizio Pittorino +1

Mixed-precision quantization (MPQ) is crucial for deploying deep neural networks on resource-constrained devices, but finding the optimal bit-width for each layer represents a comp…

cs.LG2025

TActiLE: Tiny Active LEarning for wearable devices

Massimo Pavan, Claudio Galimberti, Manuel Roveri

Tiny Machine Learning (TinyML) algorithms have seen extensive use in recent years, enabling wearable devices to be not only connected but also genuinely intelligent by running mach…