Residual Splash for Optimally Parallelizing Belief Propagation
نویسندگان
چکیده
As computer architectures move towards multicore we must build a theoretical understanding of parallelism in machine learning. In this paper we focus on parallel inference in graphical models. We demonstrate that the natural, fully synchronous parallelization of belief propagation is highly inefficient. By bounding the achievable parallel performance in chain graphical models we develop a theoretical understanding of the parallel limitations of belief propagation. We then provide a new parallel belief propagation algorithm which achieves optimal performance. Using two challenging real-world tasks, we empirically evaluate the performance of our algorithm on large cyclic graphical models where we achieve near linear parallel scaling and out perform alternative algorithms.
منابع مشابه
Parallel Splash Belief Propagation
As computer architectures transition towards exponentially increasing parallelism we are forced to adopt parallelism at a fundamental level in the design of machine learning algorithms. In this paper we focus on parallel graphical model inference. We demonstrate that the natural, synchronous parallelization of belief propagation is highly inefficient. By bounding the achievable parallel perform...
متن کاملSplash: User-friendly Programming Interface for Parallelizing Stochastic Algorithms
Stochastic algorithms are efficient approaches to solving machine learning and optimization problems. In this paper, we propose a general framework called Splash for parallelizing stochastic algorithms on multi-node distributed systems. Splash consists of a programming interface and an execution engine. Using the programming interface, the user develops sequential stochastic algorithms without ...
متن کاملParallelizing a Convergent Approximate Inference Method
The ability to efficiently perform probabilistic inference task is critical to large scale applications in statistics and artificial intelligence. Dramatic speedup might be achieved by appropriately mapping the current inference algorithms to the parallel framework. Parallel exact inference methods still suffer from exponential complexity in the worst case. Approximate inference methods have be...
متن کاملVariable-to-check residual belief propagation for LDPC codes
Variable-to-check residual belief propagation for LDPC decoding for faster convergence, better error performance and lower complexity is proposed. It is similar to residual belief propagation (RBP) that was recently applied to LDPC decoding by Vila Casado et al. because it is also a dynamic scheduling belief propagation using residuals, but it is different because the residuals are computed fro...
متن کاملDistributed Parallel Inference on Large Factor Graphs
As computer clusters become more common and the size of the problems encountered in the field of AI grows, there is an increasing demand for efficient parallel inference algorithms. We consider the problem of parallel inference on large factor graphs in the distributed memory setting of computer clusters. We develop a new efficient parallel inference algorithm, DBRSplash, which incorporates ove...
متن کامل