
Stochasticity helps to navigate rough landscapes: comparing gradientdescentbased algorithms in the phase retrieval problem
In this paper we investigate how gradientbased algorithms such as gradi...
read it

Just a Momentum: Analytical Study of MomentumBased Acceleration Methods in Paradigmatic HighDimensional NonConvex Problem
When optimizing over loss functions it is common practice to use momentu...
read it

Complex Dynamics in Simple Neural Networks: Understanding Gradient Flow in Phase Retrieval
Despite the widespread use of gradientbased algorithms for optimizing h...
read it

Dynamical meanfield theory for stochastic gradient descent in Gaussian mixture classification
We analyze in a closed form the learning dynamics of stochastic gradient...
read it

Passed & Spurious: analysing descent algorithms and local minima in spiked matrixtensor model
In this work we analyse quantitatively the interplay between the loss la...
read it

Marvels and Pitfalls of the Langevin Algorithm in Noisy Highdimensional Inference
Gradientdescentbased algorithms and their stochastic versions have wid...
read it

Approximate Survey Propagation for Statistical Inference
Approximate message passing algorithm enjoyed considerable attention in ...
read it

On the glassy nature of the hard phase in inference problems
An algorithmically hard phase was described in a range of inference prob...
read it
Pierfrancesco Urbani
is this you? claim profile