Although concern has been recently expressed with regard to the solution to the non-convex problem, convex optimization is still important in machine learning, especially when the situation requires an interpretable m...
详细信息
Although concern has been recently expressed with regard to the solution to the non-convex problem, convex optimization is still important in machine learning, especially when the situation requires an interpretable model. Solution to the convex problem is a global minimum, and the final model can be explained mathematically. Typically, the convex problem is re-casted as a regularized risk minimization problem to prevent overfitting. The cutting plane method (CPM) is one of the best solvers for the convex problem, irrespective of whether the objective function is differentiable or not. However, CPM and its variants fail to adequately address large-scale data-intensive cases because these algorithms access the entire dataset in each iteration, which substantially increases the computational burden and memory cost. To alleviate this problem, we propose a novel algorithm named the mini-batch cutting plane method (MBCPM), which iterates with estimated cutting planes calculated on a small batch of sampled data and is capable of handling large-scale problems. Furthermore, the proposed MBCPM adopts a "sink" operation that detects and adjusts noisy estimations to guarantee convergence. Numerical experiments on extensive real-world datasets demonstrate the effectiveness of MBCPM, which is superior to the bundle methods for regularized risk minimization as well as popular stochastic gradient descent methods in terms of convergence speed.
The development of multi-core processor makes the parallelization of traditional sequential algorithms increasingly important. Meanwhile, transactional memory serves a good parallel programming model. This paper takes...
详细信息
Knowledge representation learning (KRL) is one of the important research topics in artificial intelligence and Natural language processing. It can efficiently calculate the semantics of entities and relations in a low...
详细信息
Many recent applications involve processing and analyzing uncertain data. Recently, several research efforts have addressed answering skyline queries efficiently on massive uncertain datasets. However, the research la...
详细信息
Memory-intensive applications often suffer from the poor performance of disk swapping when memory is inadequate. Remote memory sharing schemes, which provide a remote memory that is faster than the local hard disk, ar...
详细信息
Unsupervised visual representation learning has gained much attention from the computer vision community because of the recent contrastive learning achievements. Current work mainly adopts instance discrimination as t...
In large-scale asynchronous distributed virtual environments(DVEs), one of the difficult problems is to deliver the concurrent events in a consistent order at each node. Generally, the previous consistency control app...
详细信息
In large-scale asynchronous distributed virtual environments(DVEs), one of the difficult problems is to deliver the concurrent events in a consistent order at each node. Generally, the previous consistency control approaches can be classified into two categories: causal order and time stamped order. However, causal order approaches can merely preserve the cause-effect relation of events and time stamped order approaches seem intrinsically complex to be used in serverless large-scale asynchronous DVEs. In this paper, we proposed a novel distributed algorithm to identify the concurrent events and preserve the consistent order delivery of them at different nodes. Simulation studies are also carried out to compare the performance of this algorithm with that of the previous ones. The results show that the new algorithm can effectively deliver the concurrent events in consistent order at each node and is more efficient than the previous algorithms in large-scale asynchronous DVEs.
Punctuation restoration in speech recognition has a wide range of application scenarios. Despite the widespread success of neural networks methods at performing punctuation restoration for English, there have been onl...
详细信息
Determining the validity of knowledge triples and filling in the missing entities or relationships in the knowledge graph are the crucial tasks for large-scale knowledge graph completion. So far, the main solutions us...
详细信息
In this paper, we explore a parallel block multigrid preconditioner based on factorization of the coefficient matrix generated in three-dimensional unstructured grids system. This preconditioner is robust with respect...
详细信息
暂无评论