paper-with-me

홈 › Papers

Learning Discrete Weights Using the Local Reparameterization Trick

2017-10-21 · ICLR 2018 1 · Oran Shayer, Dan Levi, Ethan Fetaya

Recent breakthroughs in computer vision make use of large deep neural networks, utilizing the substantial speedup offered by GPUs. For applications running on limited hardware, however, high precision real-time processing can still be a challenge. One approach to solving this problem is training networks with binary or ternary weights, thus removing the need to calculate multiplications and significantly reducing memory size. In this work, we introduce LR-nets (Local reparameterization networks), a new method for training neural networks with discrete weights using stochastic parameters. We show how a simple modification to the local reparameterization trick, previously used to train Gaussian distributed weights, enables the training of discrete weights. Using the proposed training we test both binary and ternary models on MNIST, CIFAR-10 and ImageNet benchmarks and reach state-of-the-art results on most experiments.

📄 PDF Abstract BibTeX arXiv:1710.07739

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Learning Discrete Weights and Activations Using the Local Reparameterization Trick

2023-07-04 · Guy Berger, Aviv Navon, Ethan Fetaya

In computer vision and machine learning, a crucial challenge is to lower the computation and memory demands for neural network inference. A commonplace solution to address this challenge is through the use of binarizatio…

BinarizationEfficient Neural Network

Reparameterization trick for discrete variables

2016-11-04 · Seiya Tokui, Issei Sato

Low-variance gradient estimation is crucial for learning directed graphical models parameterized by neural networks, where the reparameterization trick is widely used for those with continuous variables. While this techn…

The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables

2016-11-02 · Chris J. Maddison, andriy mnih, Yee Whye Teh

The reparameterization trick enables optimizing large scale stochastic computation graphs via gradient descent. The essence of the trick is to refactor each stochastic node into a differentiable function of its parameter…

Density EstimationStructured Prediction

Stochastic Backpropagation through Mixture Density Distributions

2016-07-19 · Alex Graves

The ability to backpropagate stochastic gradients through continuous latent distributions has been crucial to the emergence of variational autoencoders and stochastic gradient variational Bayes. The key ingredient is an …

Variational Inference

Evaluating the Variance of Likelihood-Ratio Gradient Estimators

2017-08-01 · ICML 2017 8 · Seiya Tokui, Issei Sato

The likelihood-ratio method is often used to estimate gradients of stochastic computations, for which baselines are required to reduce the estimation variance. Many types of baselines have been proposed, although th…