• AdaGrad

  • Referenced in 165 articles [sw22202]
  • function, which significantly simplifies setting a learning rate and results in regret guarantees that...
  • ADADELTA

  • Referenced in 59 articles [sw39429]
  • ADADELTA: An Adaptive Learning Rate Method. We present a novel per-dimension learning rate method ... requires no manual tuning of a learning rate and appears robust to noisy gradient information...
  • LVQ_PAK

  • Referenced in 30 articles [sw12122]
  • class zones and the optimized-learning-rate algorithm OLVQ1...
  • SVMlight

  • Referenced in 264 articles [sw04076]
  • regression, and for the problem of learning a ranking function. The optimization algorithms used ... efficient estimation methods for both error rate and precision/recall. XiAlpha-estimates [Joachims, 2002a, Joachims, 2000b ... this version is an algorithm for learning ranking functions [Joachims, 2002c]. The goal...
  • Geometer's Sketchpad

  • Referenced in 228 articles [sw04858]
  • through college—a tangible, visual way to learn mathematics that increases their engagement, understanding ... algebra by exploring ratio and proportion, rate of change, and functional relationships through numeric, tabular...
  • iPiano

  • Referenced in 60 articles [sw09623]
  • requirements of this theorem. Furthermore, a convergence rate is established for the general problem class ... computer vision problems – image denoising with learned priors and diffusion based image compression...
  • MapleCOMSPS_LRB

  • Referenced in 5 articles [sw31643]
  • solvers is the use of the learning rate branching heuristic (LRB), a departure from...
  • PVANet

  • Referenced in 4 articles [sw28335]
  • batch normalization, residual connections, and learning rate scheduling based on plateau detection. We obtained solid...
  • adaptMT

  • Referenced in 7 articles [sw30028]
  • specify any algorithm to learn local false discovery rate and a pool of convenient functions...
  • MetaGrad

  • Referenced in 1 article [sw40373]
  • MetaGrad: adaptation using multiple learning rates in online learning. We provide a new adaptive method ... general convex losses but achieves faster rates for a broad class of special functions, including ... known to imply fast rates in offline statistical learning. MetaGrad further adapts automatically ... that it simultaneously considers multiple learning rates, which are weighted directly proportional to their empirical...
  • MBT-optimizer

  • Referenced in 2 articles [sw41981]
  • algorithms, while automatically fine tuning learning rates, perform better than current state...
  • vbFRET

  • Referenced in 2 articles [sw32077]
  • smFRET time series as described in ”Learning Rates and States from Biophysical Time Series...
  • MapleSAT

  • Referenced in 2 articles [sw25918]
  • solvers is the use of the learning rate branching heuristic (LRB), a departure from...
  • DeepONet

  • Referenced in 39 articles [sw42093]
  • propose deep operator networks (DeepONets) to learn operators accurately and efficiently from a relatively small ... convergence in our computational tests, namely polynomial rates (from half order to fourth order...
  • SLEP

  • Referenced in 41 articles [sw13487]
  • SLEP: Sparse Learning with Efficient Projections. Main Features: 1) First-Order Method. At each iteration ... large-scale sparse data. 2) Optimal Convergence Rate. The convergence rate O(1/k2) is optimal...
  • HOGWILD

  • Referenced in 65 articles [sw28396]
  • performance on a variety of machine learning tasks. Several researchers have recently proposed schemes ... variable, then HOGWILD! achieves a nearly optimal rate of convergence. We demonstrate experimentally that HOGWILD...
  • Far-HO

  • Referenced in 1 article [sw25680]
  • work we show how to optimize learning rates, automatically weight the loss of single examples...
  • LVQPAK

  • Referenced in 1 article [sw25989]
  • class zones and the optimized-learning-rate algorithm OLVQ1...
  • elmNNRcpp

  • Referenced in 1 article [sw38793]
  • other parameters like learning rate, momentum, epochs, etc. This is a reimplementation of the ’elmNN ... archived. For more information, see ”Extreme learning machine: Theory and applications” by Guang-Bin Huang...
  • dagger

  • Referenced in 1 article [sw33466]
  • include model training, reinitialization, quantization, pruning, learning rate changes, checkpointing, task changes, or any other...