303 citations
- Politecnico di TorinoIT17 papers
- Sapienza University of RomeIT12 papers
- University of TurinIT10 papers
- Centre National de la Recherche ScientifiqueFR9 papers
- Collegio Carlo AlbertoIT9 papers
- Decision Sciences (United States)US7 papers
- École Polytechnique Fédérale de LausanneCH7 papers
- The Abdus Salam International Centre for Theoretical Physics (ICTP)IT7 papers
- The University of Texas at AustinUS7 papers
- University of MilanIT7 papers
- Institute for Complex SystemsIT6 papers
- Istituto Nazionale di Fisica NucleareIT6 papers
Showing 2021 · cs.LGShow all
3 papers · 2 filters
cs.LG2021★ 13 cited
Deep learning via message passing algorithms based on belief propagation
Carlo Lucibello, Fabrizio Pittorino, Gabriele Perugini +1
Message-passing algorithms based on the Belief Propagation (BP) equations constitute a well-known distributed computational scheme. It is exact on tree-like graphical models and ha…
cs.LG2021★ 28 cited
Learning through atypical "phase transitions" in overparameterized neural networks
Carlo Baldassi, Clarissa Lauditi, Enrico M. Malatesta +3
Current deep neural networks are highly overparameterized (up to billions of connection weights) and nonlinear. Yet they can fit data almost perfectly through variants of gradient…
cs.LG2021★ 8 cited
An Analytical Theory of Curriculum Learning in Teacher-Student Networks
Luca Saglietti, Stefano Sarao Mannelli, Andrew Saxe
In humans and animals, curriculum learning -- presenting data in a curated order - is critical to rapid learning and effective pedagogy. Yet in machine learning, curricula are not…