Huge training datasets for automatic speech recognition (ASR) typically contain redundant information so that a subset of data is generally enough to obtain similar ASR performance to that obtained when the entire dat...
详细信息
ISBN:
(纸本)9781538646588
Huge training datasets for automatic speech recognition (ASR) typically contain redundant information so that a subset of data is generally enough to obtain similar ASR performance to that obtained when the entire dataset is employed for training. Although the centralized submodular-based data selection methods have been successfully applied to obtain a representable subset involving the most significant information of the whole dataset, the submodular data selection conveys problems in adapting to an extremely massive dataset. This paper proposes to use distributed submodular maximization (DSM) for efficiently selecting a data subset that maintains the ASR performance, while reducing tremendously the computational overhead. There are two approaches for the distributed submodular maximization problem: one is based on an homogeneous submodular function, and the other relies on decomposable submodular functions in which heterogeneous submodular functions are applied. Our experiments show that the data subset output by the DSM algorithms can maintain the ASR performance, while significantly reducing the computational overhead. (1)
Huge training datasets for automatic speech recognition (ASR) typically contain redundant information so that a subset of data is generally enough to obtain similar ASR performance to that obtained when the entire dat...
详细信息
ISBN:
(纸本)9781538646595
Huge training datasets for automatic speech recognition (ASR) typically contain redundant information so that a subset of data is generally enough to obtain similar ASR performance to that obtained when the entire dataset is employed for training. Although the centralized submodular-based data selection methods have been successfully applied to obtain a representable subset involving the most significant information of the whole dataset, the submodular data selection conveys problems in adapting to an extremely massive dataset. This paper proposes to use distributed submodular maximization (DSM) for efficiently selecting a data subset that maintains the ASR performance, while reducing tremendously the computational overhead. There are two approaches for the distributed submodular maximization problem: one is based on an homogeneous submodular function, and the other relies on decomposable submodular functions in which heterogeneous submodular functions are applied. Our experiments show that the data subset output by the DSM algorithms can maintain the ASR performance, while significantly reducing the computational overhead.
A wide variety of problems in machine learning, including exemplar clustering, document summarization, and sensor placement, can be cast as constrained submodularmaximization problems. A lot of recent effort has been...
详细信息
ISBN:
(纸本)9781509039333
A wide variety of problems in machine learning, including exemplar clustering, document summarization, and sensor placement, can be cast as constrained submodularmaximization problems. A lot of recent effort has been devoted to developing distributed algorithms for these problems. However, these results suffer from high number of rounds, suboptimal approximation ratios, or both. We develop a framework for bringing existing algorithms in the sequential setting to the distributed setting, achieving near optimal approximation ratios for many settings in only a constant number of MapReduce rounds. Our techniques also give a fast sequential algorithm for non-monotone maximization subject to a matroid constraint.
Influence maximization-the problem of identifying a subset of k influential seeds (vertices) in a network- is a classical problem in network science with numerous applications. The problem is NP-hard, but there exist ...
详细信息
Influence maximization-the problem of identifying a subset of k influential seeds (vertices) in a network- is a classical problem in network science with numerous applications. The problem is NP-hard, but there exist efficient polynomial time approximations. However, scaling these algorithms still remain a daunting task due to the complexities associated with steps involving stochastic sampling and large-scale aggregations. In this paper, we present a new parallel distributed approximation algorithm for influence maximization with provable approximation guarantees. Our approach, which we call GreediRIS, leverages the RANDGREEDI framework-a state-of-the-art approach for distributedsubmodular optimization-for solving a step that computes a maximum k cover. GreediRIS combines distributed and streaming models of computations, along with pruning techniques, to effectively address the communication bottlenecks of the algorithm. Experimental results on up to 512 nodes (32K cores) of the NERSC Perlmutter supercomputer show that GreediRIS can achieve good strong scaling performance, preserve quality, and significantly outperform the other state-of-theart distributed implementations. For instance, on 512 nodes, the most performant variant of GreediRIS achieves geometric mean speedups of 28.99x and 36.35x for two different diffusion models, over a state-of-the-art parallel implementation. We also present a communication-optimized version of GreediRIS that further improves the speedups by two orders of magnitude.
Large scale multiagent systems must rely on distributed decision making, as centralized coordination is either impractical or impossible. Recent works approach this problem under a game theoretic lens, whereby utility...
详细信息
ISBN:
(纸本)9781713832621
Large scale multiagent systems must rely on distributed decision making, as centralized coordination is either impractical or impossible. Recent works approach this problem under a game theoretic lens, whereby utility functions are assigned to each of the agents with the hope that their local optimization approximates the centralized optimal solution. Yet, formal guarantees on the resulting performance cannot be obtained for broad classes of problems without compromising on their accuracy. In this work, we address this concern relative to the well-studied problem of resource allocation with nondecreasing concave welfare functions. We show that optimally designed local utilities achieve an approximation ratio (price of anarchy) of 1 - c/e, where c is the function's curvature and e is Euler's constant. The upshot of our contributions is the design of approximation algorithms that are distributed and efficient, and whose performance matches that of the best existing polynomial-time (and centralized) schemes.
暂无评论