Accelerating Exact and Approximate Inference for (Distributed) Discrete Optimization with GPUs

TL;DR

This paper introduces GPU-accelerated inference algorithms for discrete optimization problems, significantly improving speed and scalability in both centralized and distributed settings, enabling faster solutions for complex AI tasks.

Contribution

The paper presents a novel GPU-based inference technique that accelerates exact and approximate algorithms for discrete optimization, applicable to centralized and distributed systems.

Findings

Achieves up to 345x faster execution compared to sequential methods.

Provides up to two orders of magnitude speedup with GPU implementation.

Demonstrates scalability and efficiency in various optimization scenarios.

Abstract

Discrete optimization is a central problem in artificial intelligence. The optimization of the aggregated cost of a network of cost functions arises in a variety of problems including (W)CSP, DCOP, as well as optimization in stochastic variants such as the tasks of finding the most probable explanation (MPE) in belief networks. Inference-based algorithms are powerful techniques for solving discrete optimization problems, which can be used independently or in combination with other techniques. However, their applicability is often limited by their compute intensive nature and their space requirements. This paper proposes the design and implementation of a novel inference-based technique, which exploits modern massively parallel architectures, such as those found in Graphical Processing Units (GPUs), to speed up the resolution of exact and approximated inference-based algorithms for discrete optimization. The paper studies the proposed algorithm in both centralized and distributed optimization contexts. The paper demonstrates that the use of GPUs provides significant advantages in terms of runtime and scalability, achieving up to two orders of magnitude in speedups and showing a considerable reduction in execution time (up to 345 times faster) with respect to a sequential version.