activity
20242026
collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2025

A Probabilistic Approach to Pose Synchronization for Multi-Reference Alignment with Applications to MIMO Wireless Communication Systems

Rob Romijnders, Gabriele Cesa, Christos Louizos +2

From molecular imaging to wireless communications, the ability to align and reconstruct signals from multiple misaligned observations is crucial for system performance. We study th…

cs.LG2025

A Probabilistic Approach to Learning the Degree of Equivariance in Steerable CNNs

Lars Veefkind, Gabriele Cesa

Steerable convolutional neural networks (SCNNs) enhance task performance by modelling geometric symmetries through equivariance constraints on weights. Yet, unknown or varying symm…

cs.LG2025

Neural Lattice Reduction: A Self-Supervised Geometric Deep Learning Approach

Giovanni Luca Marchetti, Gabriele Cesa, Pratik Kumar +1

Lattice reduction is a combinatorial optimization problem aimed at finding the most orthogonal basis in a given lattice. The Lenstra-Lenstra-Lovász (LLL) algorithm is the best alg…

cs.LG2025

On the Sample Complexity of One Hidden Layer Networks with Equivariance, Locality and Weight Sharing

Arash Behboodi, Gabriele Cesa

Weight sharing, equivariance, and local filters, as in convolutional neural networks, are believed to contribute to the sample efficiency of neural networks. However, it is not cle…

cs.LG2024

Adaptive Sampling for Continuous Group Equivariant Neural Networks

Berfin Inal, Gabriele Cesa

Steerable networks, which process data with intrinsic symmetries, often use Fourier-based nonlinearities that require sampling from the entire group, leading to a need for discreti…