Kernel Machines That Adapt To Gpus For Effective Large Batch Training

No abstract is available for this paper.

• Publication year

  2018

• Venue

  USENIX workshop on Tackling computer systems problems with machine learning techniques

• Publication date

  2018-06-15

• Fields of study

  Computer Science

• Identifiers

  No identifiers available.

• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• To understand deep learning we need to understand kernel learning

  2018cited by this paper
• On the Computational Inefficiency of Large Batch Sizes for Stochastic Gradient Descent

  2018cited by this paper
• An Empirical Model of Large-Batch Training

  2018cited by this paper
• ThunderSVM: A Fast SVM Library on GPUs and CPUs

  2018cited by this paper
• Highly Scalable Deep Learning Training System with Mixed-Precision: Training ImageNet in Four Minutes

  2018cited by this paper
• Kernel Approximation Methods for Speech Recognition

  2017cited by this paper
• The Power of Interpolation: Understanding the Effectiveness of SGD in Modern Over-parametrized Learning

  2017influential reference
• Don't Decay the Learning Rate, Increase the Batch Size

  2017cited by this paper
• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour

  2017cited by this paper
• Diving into the shallows: a computational perspective on large-scale shallow learning

  2017influential reference
• Large Batch Training of Convolutional Networks

  2017cited by this paper
• FALKON: An Optimal Large Scale Kernel Method

  2017influential reference
• Faster Kernel Ridge Regression Using Sketching and Preconditioning

  2016cited by this paper
• Large Scale Kernel Learning using Block Coordinate Descent

  2016cited by this paper
• Hierarchically Compositional Kernels for Scalable Nonparametric Learning

  2016cited by this paper
• Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning

  2016cited by this paper
• Understanding deep learning requires rethinking generalization

  2016cited by this paper
• Kernel methods match Deep Neural Networks on TIMIT

  2014cited by this paper
• How to Scale Up Kernel Methods to Be As Good As Deep Neural Nets

  2014cited by this paper
• One weird trick for parallelizing convolutional neural networks

  2014cited by this paper
• Mini-Batch Primal and Dual Methods for SVMs

  2013cited by this paper
• LIBSVM: A library for support vector machines

  2011cited by this paper
• Reading Digits in Natural Images with Unsupervised Feature Learning

  2011cited by this paper
• Learning Multiple Layers of Features from Tiny Images

  2009cited by this paper
• ImageNet: A large-scale hierarchical image database

  2009cited by this paper
• Randomized Methods for Linear Constraints: Convergence Rates and Conditioning

  2008cited by this paper
• On Early Stopping in Gradient Descent Learning

  2007cited by this paper
• GradientBased Learning Applied to Document Recognition

  2001cited by this paper
• Gradient-based learning applied to document recognition

  1998cited by this paper
• DARPA TIMIT:: acoustic-phonetic continuous speech corpus CD-ROM, NIST speech disc 1-1.1

  1993cited by this paper
• Improvements in multiprocessor system design

  1985cited by this paper
• Theory of Reproducing Kernels.

  1950influential reference

• Feature maps for the Laplacian kernel and its generalizations

  2025cites this paper
• Fast Approximate Solution of Stein Equations for Post-Processing of MCMC

  2025cites this paper
• Interpretable Kernel Representation Learning at Scale: A Unified Framework Utilizing Nyström Approximation

  2025cites this paper
• xRFM: Accurate, scalable, and interpretable feature learning models for tabular data

  2025cites this paper
• Joker: Joint Optimization Framework for Lightweight Kernel Machines

  2025cites this paper
• Fast training of large kernel models with delayed projections

  2024influential citation
• Carat: Unlocking Value-Level Parallelism for Multiplier-Free GEMMs

  2024cites this paper
• Classification Performance Boosting for Interpolation Kernel Machines by Training Set Pruning Using Genetic Algorithm

  2024cites this paper
• Out of kernel tuning and optimizations for portable large-scale docking experiments on GPUs

  2024cites this paper
• A Comparison Study of Supervised Learning Techniques for the Approximation of High Dimensional Functions and Feedback Control

  2024cites this paper
• Optimal Convergence Rates for Distributed Nystroem Approximation

  2023influential citation
• Kernel Regression with Infinite-Width Neural Networks on Millions of Examples

  2023cites this paper
• On the Nystrom Approximation for Preconditioning in Kernel Machines

  2023cites this paper
• Toward Large Kernel Models

  2023influential citation
• Feature learning in neural networks and kernel machines that recursively learn features

  2022influential citation
• Efficient Hyperparameter Tuning for Large Scale Kernel Ridge Regression

  2022cites this paper
• Lecture 3: Kernel Regression

  2022cites this paper
• Cross-modal autoencoder framework learns holistic representations of cardiovascular state

  2022cites this paper
• Kernel-Based Generalized Median Computation for Consensus Learning

  2022cites this paper
• Transfer Learning with Kernel Methods

  2022cites this paper
• Mechanism of feature learning in deep fully connected networks and kernel machines that recursively learn features

  2022influential citation
• Simple, fast, and flexible framework for matrix completion with infinite width neural networks

  2021cites this paper
• Fit without fear: remarkable mathematical phenomena of deep learning through the prism of interpolation

  2021cites this paper
• Layer-Wise Relevance Propagation Based Sample Condensation for Kernel Machines

  2021influential citation
• Tensor Network Kalman Filtering for Large-Scale LS-SVMs

  2021cites this paper
• Analysis of structured deep kernel networks

  2021cites this paper
• StreaMRAK a streaming multi-resolution adaptive kernel algorithm

  2021cites this paper
• Neural Kernels Without Tangents

  2020cites this paper
• Masters Thesis: Recursive Tensor Network Bayesian Learning of Large-Scale LS-SVMs

  2020influential citation
• A lower bound for generalized median based consensus learning using kernel-induced distance functions

  2020cites this paper
• Kernel methods through the roof: handling billions of points efficiently

  2020influential citation
• Kernel Machines Beat Deep Neural Networks on Mask-based Single-channel Speech Enhancement

  2018cites this paper
• Accelerate rare

  year unknowncites this paper