Thresholds of descending algorithms in inference problems

by   Stefano Sarao Mannelli, et al.

We review recent works on analyzing the dynamics of gradient-based algorithms in a prototypical statistical inference problem. Using methods and insights from the physics of glassy systems, these works showed how to understand quantitatively and qualitatively the performance of gradient-based algorithms. Here we review the key results and their interpretation in non-technical terms accessible to a wide audience of physicists in the context of related works.


page 5

page 7


A Robust Framework for Analyzing Gradient-Based Dynamics in Bilinear Games

In this work, we establish a frequency-domain framework for analyzing gr...

Failures of Gradient-Based Deep Learning

In recent years, Deep Learning has become the go-to solution for a broad...

Nonsmooth optimal value and policy functions for mechanical systems subject to unilateral constraints

State-of-the-art approaches to optimal control of contact-rich robot dyn...

Gradient-based Taxis Algorithms for Network Robotics

Finding the physical location of a specific network node is a prototypic...

Behind the Scenes of Gradient Descent: A Trajectory Analysis via Basis Function Decomposition

This work analyzes the solution trajectory of gradient-based algorithms ...

Statistical physics of inference: Thresholds and algorithms

Many questions of fundamental interest in todays science can be formulat...

On recent advances in 2D Constrained Delaunay triangulation algorithms

In this article, recent works on 2D Constrained Delaunay triangulation(C...

Please sign up or login with your details

Forgot password? Click here to reset