collaborators

6 papers

stat.ML2026

A Diffusion Approximation for Temporal-Difference Learning with Linear Features under Markovian Noise

M. Forzo, E. Monzio Compagnoni, A. Russo +1

Temporal difference (TD) learning with linear function approximation is a core method for policy evaluation. Its classical continuous-time description is an ordinary differential e…

cs.LG2026

Beyond a Single Explanation of the Adam--SGD Gap

Chenxiang Zhang, Rustem Islamov, Enea Monzio Compagnoni +3

Prior work has identified several factors that can contribute to the performance gap between Adam and SGD, spanning data aspects, architecture design, and optimization properties.…

cs.LG2026

On the Interaction of Batch Noise, Adaptivity, and Compression, under -Smoothness: An SDE Approach

Enea Monzio Compagnoni, Rustem Islamov, Frank Norbert Proske +3

Distributed stochastic optimization intertwines (i) stochastic gradient noise, (ii) communication compression, and (iii) adaptive/normalized updates. While each factor has been stu…

cs.LG2026

Adaptive Methods Are Preferable in High Privacy Settings: An SDE Perspective

Enea Monzio Compagnoni, Alessandro Stanghellini, Rustem Islamov +2

Differential Privacy (DP) is becoming central to large-scale training as privacy regulations tighten. We revisit how DP noise interacts with adaptivity in optimization through the…

cs.LG2025

Adaptive Methods through the Lens of SDEs: Theoretical Insights on the Role of Noise

Enea Monzio Compagnoni, Tianlin Liu, Rustem Islamov +3

Despite the vast empirical evidence supporting the efficacy of adaptive optimization methods in deep learning, their theoretical understanding is far from complete. This work intro…

cs.LG2025

Unbiased and Sign Compression in Distributed Learning: Comparing Noise Resilience via SDEs

Enea Monzio Compagnoni, Rustem Islamov, Frank Norbert Proske +1

Distributed methods are essential for handling machine learning pipelines comprising large-scale models and datasets. However, their benefits often come at the cost of increased co…