
Wide flat minima and optimal generalization in classifying highdimensional Gaussian mixtures
We analyze the connection between minimizers with good generalizing prop...
read it

Entropic gradient descent algorithms and wide flat minima
The properties of flat minima in the empirical risk landscape of neural ...
read it

Clustering of solutions in the symmetric binary perceptron
The geometrical features of the (nonconvex) loss landscape of neural ne...
read it

Natural representation of composite data with replicated autoencoders
Generative processes in biology and other fields often produce data that...
read it

On the geometry of solutions and on the capacity of multilayer neural networks with ReLU activations
Rectified Linear Units (ReLU) have become the main model for the neural ...
read it

Shaping the learning landscape in neural networks around wide flat minima
Learning in Deep Neural Networks (DNN) takes place by minimizing a nonc...
read it

On the role of synaptic stochasticity in training lowprecision neural networks
Stochasticity and limited precision of synaptic weights in neural networ...
read it

Parle: parallelizing stochastic gradient descent
We propose a new algorithm called Parle for parallel training of deep ne...
read it

Efficiency of quantum versus classical annealing in nonconvex learning problems
Quantum annealers aim at solving nonconvex optimization problems by exp...
read it

EntropySGD: Biasing Gradient Descent Into Wide Valleys
This paper proposes a new optimization algorithm called EntropySGD for ...
read it

Unreasonable Effectiveness of Learning Neural Networks: From Accessible States and Robust Ensembles to Basic Algorithmic Schemes
In artificial neural networks, learning from data is a computationally d...
read it

Learning may need only a few bits of synaptic precision
Learning in neural networks poses peculiar challenges when using discret...
read it

Local entropy as a measure for sampling solutions in Constraint Satisfaction Problems
We introduce a novel Entropydriven Monte Carlo (EdMC) strategy to effic...
read it

Subdominant Dense Clusters Allow for Simple Learning and High Computational Performance in Neural Networks with Discrete Synapses
We show that discrete synaptic weights can be efficiently used for learn...
read it

Message passing for quantified Boolean formulas
We introduce two types of message passing algorithms for quantified Bool...
read it
Riccardo Zecchina
is this you? claim profile