Carlo Baldassi
Orcid: 0000-0002-5451-8388
According to our database1,
Carlo Baldassi
authored at least 32 papers
between 2007 and 2023.
Collaborative distances:
Collaborative distances:
Timeline
Legend:
Book In proceedings Article PhD thesis Dataset OtherLinks
On csauthors.net:
Bibliography
2023
Typical and atypical solutions in non-convex neural networks with discrete and continuous weights.
CoRR, 2023
2022
Systematically and efficiently improving $k$-means initialization by pairwise-nearest-neighbor smoothing.
Trans. Mach. Learn. Res., 2022
Recombinator-k-Means: An Evolutionary Algorithm That Exploits k-Means++ for Recombination.
IEEE Trans. Evol. Comput., 2022
Systematically improving existing k-means initialization algorithms at nearly no cost, by pairwise-nearest-neighbor smoothing.
CoRR, 2022
Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry.
Proceedings of the International Conference on Machine Learning, 2022
2021
CoRR, 2021
CoRR, 2021
Proceedings of the 9th International Conference on Learning Representations, 2021
2020
Proceedings of the Protein-Protein Interaction Networks, Methods and Protocols., 2020
Proc. Natl. Acad. Sci. USA, 2020
A Behavioral Characterization of the Drift Diffusion Model and Its Multialternative Extension for Choice Under Time Pressure.
Manag. Sci., 2020
Wide flat minima and optimal generalization in classifying high-dimensional Gaussian mixtures.
CoRR, 2020
2019
On the geometry of solutions and on the capacity of multi-layer neural networks with ReLU activations.
CoRR, 2019
CoRR, 2019
2018
Proc. Natl. Acad. Sci. USA, 2018
2017
CoRR, 2017
CoRR, 2017
Proceedings of the 5th International Conference on Learning Representations, 2017
2016
Unreasonable effectiveness of learning neural networks: From accessible states and robust ensembles to basic algorithmic schemes.
Proc. Natl. Acad. Sci. USA, 2016
Unreasonable Effectiveness of Learning Neural Nets: Accessible States and Robust Ensembles.
CoRR, 2016
2015
Binary Synapse Circuitry for High Efficiency Learning Algorithm Using Generalized Boundary Condition Memristor Models.
Proceedings of the Advances in Neural Networks: Computational and Theoretical Issues, 2015
A Three-Threshold Learning Rule Approaches the Maximal Capacity of Recurrent Neural Networks.
PLoS Comput. Biol., 2015
2014
Sharing Information to Reconstruct Patient-Specific Pathways in Heterogeneous Diseases.
Proceedings of the Biocomputing 2014: Proceedings of the Pacific Symposium, 2014
2013
Shape Similarity, Better than Semantic Membership, Accounts for the Structure of Visual Object Representations in a Population of Monkey Inferotemporal Neurons.
PLoS Comput. Biol., 2013
2007
Proc. Natl. Acad. Sci. USA, 2007