• Pegasos

  • Referenced in 98 articles [sw08752]
  • resulting algorithm is especially suited for learning from large datasets. Our approach also extends ... demonstrate an order-of-magnitude speedup over previous SVM learning methods...
  • PEBBL

  • Referenced in 12 articles [sw13809]
  • machine learning applications. For sufficiently difficult problem instances, we show essentially linear speedup on over...
  • NodeSketch

  • Referenced in 1 article [sw32346]
  • usually require significant computational resources for the learning process, which hinders their applications on large ... while showing significant speedup of 9x-372x in the embedding learning process...
  • SAGE

  • Referenced in 2 articles [sw29919]
  • particular domains such as multimedia and learning algorithms, approximation is commonly used today. We consider ... selects among the available kernels to achieve speedup while adhering to a target output quality ... learning and image processing kernels, SAGE’s approximation yields an average of 2.5x speedup...
  • SHIELD

  • Referenced in 7 articles [sw20121]
  • this work, we describe an optimized Ring Learning With Errors (RLWE) based implementation ... features of the system to achieve significant speedup over the state...
  • ParMAC

  • Referenced in 0 articles [sw15226]
  • learning binary autoencoders. Many powerful machine learning models are based on the composition of multiple ... runtime and parallel speedup. We develop ParMAC to learn binary autoencoders for fast, approximate image ... distributed system and demonstrate nearly perfect speedups in a 128-processor cluster with a training...
  • CYCLADES

  • Referenced in 3 articles [sw15227]
  • CYCLADES: Conflict-free Asynchronous Machine Learning. We present CYCLADES, a general framework for parallelizing stochastic ... offers a black-box analysis for provable speedups across a large family of algorithms...
  • Celer

  • Referenced in 4 articles [sw37123]
  • regularizations are ubiquitous in high-dimensional machine learning, but solving the resulting optimization problems ... dual point construction, we show significant computational speedups on multiple real-world problems...
  • CANTINA+

  • Referenced in 1 article [sw36772]
  • engines and third party services with machine learning techniques to detect phish. Moreover, we designed ... help reduce FP and achieve runtime speedup. The first is a near-duplicate phish detector...
  • NeuroVectorizer

  • Referenced in 1 article [sw32381]
  • extend our framework to support multiple supervised learning methods. We evaluate our approaches against ... experiments show 1.29X-4.73X performance speedup compared to baseline and only 3% worse...
  • LCNN

  • Referenced in 1 article [sw39591]
  • weights in CNNs. Training LCNN involves jointly learning a dictionary and a small ... show that LCNN can offer 3.2x speedup while achieving 55.1% top-1 accuracy using AlexNet ... benefits of LCNN in few-shot learning and few-iteration learning, two crucial aspects...
  • apricot

  • Referenced in 1 article [sw37194]
  • Apricot is extremely efficient, using both algorithmic speedups such as the lazy greedy algorithm ... subset selection by training machine learning models to comparable accuracy using either the full data...
  • AnyDBC

  • Referenced in 2 articles [sw29968]
  • like existing techniques, AnyDBC iteratively and actively learns the current cluster structure of the data ... exact final result of DBSCAN. Experiments show speedup factors of orders of magnitude compared...
  • GPipe

  • Referenced in 4 articles [sw39466]
  • improving model quality for several different machine learning tasks. In many cases, increasing model capacity ... splitting pipelining algorithm, resulting in almost linear speedup when a model is partitioned across multiple...
  • AMC

  • Referenced in 2 articles [sw36241]
  • provide the model compression policy. This learning-based compression policy outperforms conventional rule-based compression ... pipeline to MobileNet and achieved 1.81x speedup of measured inference latency on an Android...
  • PipeLayer

  • Referenced in 1 article [sw35258]
  • networks (CNNs) are the heart of deep learning applications. Recent works PRIME [1] and ISAAC ... experiment results show that, PipeLayer achieves the speedup of 42.45x compared with GPU platform...
  • GoGP

  • Referenced in 1 article [sw23912]
  • scale datasets and to accommodate an online learning setting where data arrive irregularly ... performance while achieving a magnitude of computational speedup compared with its rivals under online setting...
  • ATLAS

  • Referenced in 198 articles [sw00056]
  • This paper describes the Automatically Tuned Linear Algebra...
  • MapReduce

  • Referenced in 257 articles [sw00546]
  • MapReduce is a new parallel programming model initially...
  • Matlab

  • Referenced in 13100 articles [sw00558]
  • MATLAB® is a high-level language and interactive...