Gradient-based saliency maps are widely used to explain deep neural network
decisions. However, as models become deeper and more black-box, such as in
closed-source APIs like ChatGPT, computing gradients become challenging,
hindering conventional explanation methods. In this work, we introduce a novel
unified framework for estimating gradients in black-box settings and generating
saliency maps to interpret model decisions. We employ the likelihood ratio
method to estimate output-to-input gradients and utilize them for saliency map
generation. Additionally, we propose blockwise computation techniques to
enhance estimation accuracy. Extensive experiments in black-box settings
validate the effectiveness of our method, demonstrating accurate gradient
estimation and explainability of generated saliency maps. Furthermore, we
showcase the scalability of our approach by applying it to explain GPT-Vision,
revealing the continued relevance of gradient-based explanation methods in the
era of large, closed-source, and black-box models.

我们引入了一种新的统一框架，用于在黑盒模型中估计梯度并生成显著性地图以解释模型决策。我们采用似然比方法来估计输出到输入的梯度，并利用它们来生成显著性地图。此外，我们提出了块计算技术来提高估计精度。在黑盒模型中进行的大量实验证实了我们方法的有效性，表明准确估计梯度并生成的显著性地图能够解释模型的决策。此外，我们将该方法应用于解释 GPT-Vision，展示了在大规模、闭源和黑盒模型时梯度解释方法的可伸缩性。

基于梯度的黑盒显著图生成的前向学习

Forward Learning for Gradient-based Black-box Saliency Map Generation

Efficient and biologically plausible alternatives to backpropagation in
neural network training remain a challenge due to issues such as high
computational complexity and additional assumptions about neural networks,
which limit scalability to deeper networks. The likelihood ratio method offers
a promising gradient estimation strategy but is constrained by significant
memory consumption, especially when deploying multiple copies of data to reduce
estimation variance. In this paper, we introduce an approximation technique for
the likelihood ratio (LR) method to alleviate computational and memory demands
in gradient estimation. By exploiting the natural parallelism during the
backward pass using LR, we further provide a high-performance training
strategy, which pipelines both the forward and backward pass, to make it more
suitable for the computation on specialized hardware. Extensive experiments
demonstrate the effectiveness of the approximation technique in neural network
training. This work underscores the potential of the likelihood ratio method in
achieving high-performance neural network training, suggesting avenues for
further exploration.

通过利用自然的并行性和高性能训练策略，介绍了似然比方法在神经网络训练中的潜力及其逼近技术在梯度估计中的有效性。

近似似然比：增强神经网络训练的正向唯一和并行框架

Approximated Likelihood Ratio: A Forward-Only and Parallel Framework for  Boosting Neural Network Training

Backpropagation (BP) is the most important gradient estimation method for
training neural networks in deep learning. However, the literature shows that
neural networks trained by BP are vulnerable to adversarial attacks. We develop
the likelihood ratio (LR) method, a new gradient estimation method, for
training a broad range of neural network architectures, including convolutional
neural networks, recurrent neural networks, graph neural networks, and spiking
neural networks, without recursive gradient computation. We propose three
methods to efficiently reduce the variance of the gradient estimation in the
neural network training process. Our experiments yield numerical results for
training different neural networks on several datasets. All results demonstrate
that the LR method is effective for training various neural networks and
significantly improves the robustness of the neural networks under adversarial
attacks relative to the BP method.

本研究提出了一种新的梯度估计方法 —— 似然比方法，用于从事各种神经网络体系结构的训练，并且相对于反向传播法，该方法能够显著提高神经网络对抗性攻击的鲁棒性。

使用似然比方法进行神经网络训练：深入探讨无需反向传播的技术

Training Neural Networks without Backpropagation: A Deeper Dive into the  Likelihood Ratio Method

We consider the problem of control in the setting of reinforcement learning
(RL), where model information is not available. Policy gradient algorithms are
a popular solution approach for this problem and are usually shown to converge
to a stationary point of the value function. In this paper, we propose two
policy Newton algorithms that incorporate cubic regularization. Both algorithms
employ the likelihood ratio method to form estimates of the gradient and
Hessian of the value function using sample trajectories. The first algorithm
requires an exact solution of the cubic regularized problem in each iteration,
while the second algorithm employs an efficient gradient descent-based
approximation to the cubic regularized problem. We establish convergence of our
proposed algorithms to a second-order stationary point (SOSP) of the value
function, which results in the avoidance of traps in the form of saddle points.
In particular, the sample complexity of our algorithms to find an
$\epsilon$-SOSP is $O(\epsilon^{-3.5})$, which is an improvement over the
state-of-the-art sample complexity of $O(\epsilon^{-4.5})$.

论文探讨了基于强化学习的控制问题，提出了两种策略牛顿算法，并证明了算法的渐进收敛性和样本复杂度。