Picture for Carlo Baldassi

Carlo Baldassi

Typical and atypical solutions in non-convex neural networks with discrete and continuous weights

Add code
Apr 26, 2023
Viaarxiv icon

Systematically improving existing k-means initialization algorithms at nearly no cost, by pairwise-nearest-neighbor smoothing

Add code
Feb 08, 2022
Figure 1 for Systematically improving existing k-means initialization algorithms at nearly no cost, by pairwise-nearest-neighbor smoothing
Figure 2 for Systematically improving existing k-means initialization algorithms at nearly no cost, by pairwise-nearest-neighbor smoothing
Figure 3 for Systematically improving existing k-means initialization algorithms at nearly no cost, by pairwise-nearest-neighbor smoothing
Figure 4 for Systematically improving existing k-means initialization algorithms at nearly no cost, by pairwise-nearest-neighbor smoothing
Viaarxiv icon

Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry

Add code
Feb 07, 2022
Figure 1 for Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry
Figure 2 for Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry
Figure 3 for Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry
Figure 4 for Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry
Viaarxiv icon

Quantum Approximate Optimization Algorithm applied to the binary perceptron

Add code
Dec 19, 2021
Figure 1 for Quantum Approximate Optimization Algorithm applied to the binary perceptron
Figure 2 for Quantum Approximate Optimization Algorithm applied to the binary perceptron
Figure 3 for Quantum Approximate Optimization Algorithm applied to the binary perceptron
Figure 4 for Quantum Approximate Optimization Algorithm applied to the binary perceptron
Viaarxiv icon

Learning through atypical ''phase transitions'' in overparameterized neural networks

Add code
Oct 01, 2021
Figure 1 for Learning through atypical ''phase transitions'' in overparameterized neural networks
Figure 2 for Learning through atypical ''phase transitions'' in overparameterized neural networks
Figure 3 for Learning through atypical ''phase transitions'' in overparameterized neural networks
Figure 4 for Learning through atypical ''phase transitions'' in overparameterized neural networks
Viaarxiv icon

Unveiling the structure of wide flat minima in neural networks

Add code
Jul 02, 2021
Figure 1 for Unveiling the structure of wide flat minima in neural networks
Figure 2 for Unveiling the structure of wide flat minima in neural networks
Figure 3 for Unveiling the structure of wide flat minima in neural networks
Figure 4 for Unveiling the structure of wide flat minima in neural networks
Viaarxiv icon

Wide flat minima and optimal generalization in classifying high-dimensional Gaussian mixtures

Add code
Oct 27, 2020
Figure 1 for Wide flat minima and optimal generalization in classifying high-dimensional Gaussian mixtures
Figure 2 for Wide flat minima and optimal generalization in classifying high-dimensional Gaussian mixtures
Figure 3 for Wide flat minima and optimal generalization in classifying high-dimensional Gaussian mixtures
Figure 4 for Wide flat minima and optimal generalization in classifying high-dimensional Gaussian mixtures
Viaarxiv icon

Ergodic Annealing

Add code
Aug 01, 2020
Figure 1 for Ergodic Annealing
Figure 2 for Ergodic Annealing
Figure 3 for Ergodic Annealing
Viaarxiv icon

Entropic gradient descent algorithms and wide flat minima

Add code
Jun 14, 2020
Figure 1 for Entropic gradient descent algorithms and wide flat minima
Figure 2 for Entropic gradient descent algorithms and wide flat minima
Figure 3 for Entropic gradient descent algorithms and wide flat minima
Figure 4 for Entropic gradient descent algorithms and wide flat minima
Viaarxiv icon

Multialternative Neural Decision Processes

Add code
May 16, 2020
Viaarxiv icon