most citedClustering in pure-attention hardmax transformers and its role in sentiment analysis

1 citations · 2 across the 4 of their papers we have counts for

collaborators

5 papers

math.OC2026

Finite convergence and minimizer extraction in moment relaxations with correlative sparsity

Giovanni Fantuzzi, Federico Fuentes

We identify a new sufficient condition for the finite convergence of moment relaxations of polynomial optimization problems with correlative sparsity. This condition, which follows…

cs.LG20261 cited

Exact Sequence Interpolation with Transformers

Albert Alcalde, Giovanni Fantuzzi, Enrique Zuazua

We prove that transformers can exactly interpolate datasets of finite input sequences in , , with corresponding output sequences of smaller or equal length.…

cs.CL20261 cited

Clustering in pure-attention hardmax transformers and its role in sentiment analysis

Albert Alcalde, Giovanni Fantuzzi, Enrique Zuazua

Transformers are extremely successful machine learning models whose mathematical properties remain poorly understood. Here, we rigorously characterize the behavior of transformers…

math.DS2026

Data-driven discovery of polynomial ODEs with provably bounded solutions

Albert Alcalde, Giovanni Fantuzzi

We introduce SILAS, a data-driven framework for discovering polynomial ordinary differential equations (ODEs) with provably bounded trajectories. Boundedness is certified by compac…

math.OC2025

Moment-SOS hierarchies for arrow-type polynomial matrix inequalities with applications to structural optimization

Marouan Handa, Marek Tyburec, Giovanni Fantuzzi +2

The Arrow Decomposition (AD) technique, initially introduced in [Mathematical Programming 190(1-2) (2021), pp 105-134], demonstrated superior scalability over the classical chordal…