11 papers
A Unified Framework for Quantized and Continuous Strong Lottery Tickets
Aakash Kumar, Emanuele Natale
The Strong Lottery Ticket Hypothesis (SLTH) asserts that sufficiently overparameterized, randomly initialized neural networks contain sparse subnetworks that, even without any trai…
Structured vs. Unstructured Pruning: An Exponential Gap
Davide Ferre', Frédéric Giroire, Frederik Mallmann-Trenn +1
The Strong Lottery Ticket Hypothesis (SLTH) states that large, randomly initialized neural networks contain sparse subnetworks capable of approximating a target function at initial…
Compositional Generalization in Autoregressive Models via Logit Composition
Aakash Kumar, Maria Sofia Bucarelli, Emanuele Natale
Composing autoregressive models remains a core challenge in understanding how large language models can combine behaviors or skills learned across tasks. We introduce a new and pri…
Beyond Fixed Points: Superpolynomial Capacity of Asymmetric Hopfield Networks
Aakash Kumar, Anatoly Khina, Frederik Mallmann-Trenn +1
Classical Hopfield networks are limited to static patterns due to symmetric weights, whereas asymmetric networks can encode temporal sequences via limit-cycle attractors. Achieving…
DejaVu: A Minimalistic Mechanism for Distributed Plurality Consensus
Francesco d'Amore, Niccolò D'Archivio, George Giakkoupis +2
We study the plurality consensus problem in distributed systems where a population of extremely simple agents, each initially holding one of opinions, aims to agree on the init…
Intermittent Cauchy walks enable optimal 3D search across target shapes and sizes
Matteo Stromieri, Emanuele Natale, Amos Korman
Target shape, not just size, plays a pivotal role in determining detectability during random search. We analyze intermittent Lévy walks in three dimensions, and mathematically pro…