An autoencoder compression approach for accelerating large-scale inverse problems

by   Jonathan Wittmer, et al.

PDE-constrained inverse problems are some of the most challenging and computationally demanding problems in computational science today. Fine meshes that are required to accurately compute the PDE solution introduce an enormous number of parameters and require large scale computing resources such as more processors and more memory to solve such systems in a reasonable time. For inverse problems constrained by time dependent PDEs, the adjoint method that is often employed to efficiently compute gradients and higher order derivatives requires solving a time-reversed, so-called adjoint PDE that depends on the forward PDE solution at each timestep. This necessitates the storage of a high dimensional forward solution vector at every timestep. Such a procedure quickly exhausts the available memory resources. Several approaches that trade additional computation for reduced memory footprint have been proposed to mitigate the memory bottleneck, including checkpointing and compression strategies. In this work, we propose a close-to-ideal scalable compression approach using autoencoders to eliminate the need for checkpointing and substantial memory storage, thereby reducing both the time-to-solution and memory requirements. We compare our approach with checkpointing and an off-the-shelf compression approach on an earth-scale ill-posed seismic inverse problem. The results verify the expected close-to-ideal speedup for both the gradient and Hessian-vector product using the proposed autoencoder compression approach. To highlight the usefulness of the proposed approach, we combine the autoencoder compression with the data-informed active subspace (DIAS) prior to show how the DIAS method can be affordably extended to large scale problems without the need of checkpointing and large memory.


page 6

page 7

page 11

page 12

page 14

page 17


Neural Inverse Operators for Solving PDE Inverse Problems

A large class of inverse problems for PDEs are only well-defined as mapp...

Lossy Compression for Large Scale PDE Problems

Solvers for partial differential equations (PDE) are one of the cornerst...

Convergence analysis for forward and inverse problems in singularly perturbed time-dependent reaction-advection-diffusion equations

In this paper, by employing the asymptotic method, we prove the existenc...

Learning to compress and search visual data in large-scale systems

The problem of high-dimensional and large-scale representation of visual...

Solving forward and inverse problems in a non-linear 3D PDE via an asymptotic expansion based approach

This paper is concerned with the usage of the asymptotic expansion metho...

On inverse problems modeled by PDE's

We investigate the iterative methods proposed by Maz'ya and Kozlov (see ...

Learned Optimizers for Analytic Continuation

Traditional maximum entropy and sparsity-based algorithms for analytic c...

Please sign up or login with your details

Forgot password? Click here to reset