collaborators

6 papers

stat.ML2026

On Universality of Deep Equivariant Networks

Marco Pacini, Mircea Petrache, Bruno Lepri +2

Universality results for equivariant neural networks remain rare. Those that do exist typically hold only in restrictive settings: either they rely on regular or higher-order tenso…

cs.LG2026

Recurrent Equivariant Constraint Modulation: Learning Per-Layer Symmetry Relaxation from Data

Stefanos Pertigkiozoglou, Mircea Petrache, Shubhendu Trivedi +1

Equivariant neural networks exploit underlying task symmetries to improve generalization, but strict equivariance constraints can induce more complex optimization dynamics that can…

cs.LG2025

Three iterations of -WL test distinguish non isometric clouds of -dimensional points

Valentino Delle Rose, Alexander Kozachinskiy, Cristóbal Rojas +2

The Weisfeiler--Lehman (WL) test is a fundamental iterative algorithm for checking isomorphism of graphs. It has also been observed that it underlies the design of several graph ne…

stat.ML2025

Symmetry-Based Structured Matrices for Efficient Approximately Equivariant Networks

Ashwin Samudre, Mircea Petrache, Brian D. Nord +1

There has been much recent interest in designing neural networks (NNs) with relaxed equivariance, which interpolate between exact equivariance and full flexibility for consistent p…

cs.LG2025

Approximation-Generalization Trade-offs under (Approximate) Group Equivariance

Mircea Petrache, Shubhendu Trivedi

The explicit incorporation of task-specific inductive biases through symmetry has emerged as a general design precept in the development of high-performance machine learning models…

math.OC2025

Optimal quantization with branched optimal transport distances

Paul Pegon, Mircea Petrache

We consider the problem of optimal approximation of a target measure by an atomic measure with atoms, in branched optimal transport distance. This is a new branched transport v…