Efficient implementation of incremental proximal-point methods

05/03/2022
by   Alex Shtoff, et al.
0

Model training algorithms which observe a small portion of the training set in each computational step are ubiquitous in practical machine learning, and include both stochastic and online optimization methods. In the vast majority of cases, such algorithms typically observe the training samples via the gradients of the cost functions the samples incur. Thus, these methods exploit are the slope of the cost functions via their first-order approximations. To address limitations of gradient-based methods, such as sensitivity to step-size choice in the stochastic setting, or inability to exploit small function variability in the online setting, several streams of research attempt to exploit more information about the cost functions than just their gradients via the well-known proximal framework of optimization. However, implementing such methods in practice poses a challenge, since each iteration step boils down to computing a proximal operator, which may not be easy. In this work we provide efficient algorithms and corresponding implementations of proximal operators in order to make experimentation with incremental proximal optimization algorithms accessible to a larger audience of researchers and practitioners, and in particular to promote additional theoretical research into these methods by closing the gap between their theoretical description in research papers and their use in practice. The corresponding code is published at https://github.com/alexshtf/inc_prox_pt.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/18/2023

Variance reduction techniques for stochastic proximal point algorithms

In the context of finite sums minimization, variance reduction technique...
research
05/03/2020

Riemannian Stochastic Proximal Gradient Methods for Nonsmooth Optimization over the Stiefel Manifold

Riemannian optimization has drawn a lot of attention due to its wide app...
research
07/12/2018

The Incremental Proximal Method: A Probabilistic Perspective

In this work, we highlight a connection between the incremental proximal...
research
12/07/2021

Shrub Ensembles for Online Classification

Online learning algorithms have become a ubiquitous tool in the machine ...
research
01/27/2023

Adapting Step-size: A Unified Perspective to Analyze and Improve Gradient-based Methods for Adversarial Attacks

Learning adversarial examples can be formulated as an optimization probl...
research
08/21/2023

GBM-based Bregman Proximal Algorithms for Constrained Learning

As the complexity of learning tasks surges, modern machine learning enco...

Please sign up or login with your details

Forgot password? Click here to reset