639 citations · 2.9k across the 94 of their papers we have counts for
98 papers
A Bregman Proximal Viewpoint on Neural Operators
Abdel-Rahim Mezidi, Jordan Patracone, Saverio Salzo +4
We present several advances on neural operators by viewing the action of operator layers as the minimizers of Bregman regularized optimization problems over Banach function spaces.…
AdaGrad does not adapt to Hölder-smoothness for composite objectives
Matia Bojovic, Saverio Salzo, Massimiliano Pontil
We exhibit a simple deterministic one-dimensional convex composite optimization problem for which AdaGrad scheme does not achieve the classical convergence rate $\mathcal{O}(n^{-(1…
Bilevel learning
Riccardo Grazzi, Massimiliano Pontil, Saverio Salzo +1
Bilevel learning refers to machine learning problems that can be formulated as bilevel optimization models, where decisions are organized in a hierarchical structure. This paradigm…
AdaGrad-Diff: A New Version of the Adaptive Gradient Algorithm
Matia Bojovic, Saverio Salzo, Massimiliano Pontil
Vanilla gradient methods are often highly sensitive to the choice of stepsize, which typically requires manual tuning. Adaptive methods alleviate this issue and have therefore beco…
DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products
Julien Siems, Timur Carstensen, Arber Zela +3
Linear Recurrent Neural Networks (linear RNNs) have emerged as competitive alternatives to Transformers for sequence modeling, offering efficient training and linear-time inference…
Adaptive AI-Driven Material Synthesis: Towards Autonomous 2D Materials Growth
Leonardo Sabattini, Annalisa Coriolano, Corneel Casert +7
Two-dimensional (2D) materials are poised to revolutionize current solid-state technology with their extraordinary properties. Yet, the primary challenge remains their scalable pro…