On the modes of convergence of Stochastic Optimistic Mirror Descent (OMD) for saddle point problems

08/02/2019
by   Yanting Ma, et al.
0

In this article, we study the convergence of Mirror Descent (MD) and Optimistic Mirror Descent (OMD) for saddle point problems satisfying the notion of coherence as proposed in Mertikopoulos et al. We prove convergence of OMD with exact gradients for coherent saddle point problems, and show that monotone convergence only occurs after some sufficiently large number of iterations. This is in contrast to the claim in Mertikopoulos et al. of monotone convergence of OMD with exact gradients for coherent saddle point problems. Besides highlighting this important subtlety, we note that the almost sure convergence guarantees of MD and OMD with stochastic gradients for strictly coherent saddle point problems that are claimed in Mertikopoulos et al. are not fully justified by their proof. As such, we fill out the missing details in the proof and as a result have only been able to prove convergence with high probability. We would like to note that our analysis relies heavily on the core ideas and proof techniques introduced in Zhou et al. and Mertikopoulos et al., and we only aim to re-state and correct the results in light of what we were able to prove rigorously while filling in the much needed missing details in their proofs.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/15/2022

Further Collapses in TFNP

We show =∩. Here the class consists of all total search problems that r...
research
06/30/2021

Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth Games: Convergence Analysis under Expected Co-coercivity

Two of the most prominent algorithms for solving unconstrained smooth ga...
research
09/30/2020

Erratum Concerning the Obfuscated Gradients Attack on Stochastic Activation Pruning

Stochastic Activation Pruning (SAP) (Dhillon et al., 2018) is a defense ...
research
07/09/2021

Darlin: A proof carrying data scheme based on Marlin

In this document we describe the Darlin proof carrying data scheme for t...
research
07/20/2021

QRAT Polynomially Simulates Merge Resolution

Merge Resolution (MRes [Beyersdorff et al. J. Autom. Reason.'2021] ) is ...
research
05/21/2018

Implicit Probabilistic Integrators for ODEs

We introduce a family of implicit probabilistic integrators for initial ...
research
08/20/2022

Adam Can Converge Without Any Modification on Update Rules

Ever since Reddi et al. 2018 pointed out the divergence issue of Adam, m...

Please sign up or login with your details

Forgot password? Click here to reset