论文标题
随机二进制网络的路径样品分析梯度估计器
Path Sample-Analytic Gradient Estimators for Stochastic Binary Networks
论文作者
论文摘要
在具有二元激活和 /或二元权重的神经网络中，由于模型具有分段恒定响应，因此梯度下降的训练是复杂的。我们考虑通过在激活前添加声音获得的随机二进制网络。预期的模型响应成为参数的平滑函数，其梯度定义得很好，但是准确估算它是一项挑战。我们提出了一种结合采样和分析近似步骤的估计问题的新方法。与现有的无偏见和有偏见的估计量相比，该方法以小偏见的价格显着降低了差异，这给出了非常实际的权衡。我们进一步表明，一个额外的线性化步骤导致先前仅被称为临时启发式的深度直通估计器。我们在实验上显示出更高的梯度估计准确性，并在使用两种建议的方法中表现出更稳定，更好的性能训练。
In neural networks with binary activations and or binary weights the training by gradient descent is complicated as the model has piecewise constant response. We consider stochastic binary networks, obtained by adding noises in front of activations. The expected model response becomes a smooth function of parameters, its gradient is well defined but it is challenging to estimate it accurately. We propose a new method for this estimation problem combining sampling and analytic approximation steps. The method has a significantly reduced variance at the price of a small bias which gives a very practical tradeoff in comparison with existing unbiased and biased estimators. We further show that one extra linearization step leads to a deep straight-through estimator previously known only as an ad-hoc heuristic. We experimentally show higher accuracy in gradient estimation and demonstrate a more stable and better performing training in deep convolutional models with both proposed methods.
