Sharper Bounds for Proximal Gradient Algorithms with Errors

03/04/2022
by   Anis Hamadouche, et al.
0

We analyse the convergence of the proximal gradient algorithm for convex composite problems in the presence of gradient and proximal computational inaccuracies. We derive new tighter deterministic and probabilistic bounds that we use to verify a simulated (MPC) and a synthetic (LASSO) optimization problems solved on a reduced-precision machine in combination with an inaccurate proximal operator. We also show how the probabilistic bounds are more robust for algorithm verification and more accurate for application performance guarantees. Under some statistical assumptions, we also prove that some cumulative error terms follow a martingale property. And conforming to observations, e.g., in <cit.>, we also show how the acceleration of the algorithm amplifies the gradient and proximal computational errors.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset