We study the problem of learning disentangled signals from data using non-linear Independent Component Analysis (ICA). Motivated by advances in self-supervised learning, we propose to learn self-sufficient signals: A recovered signal should be able to reconstruct a missing value of its own from all remaining components without relying on any other signals. We formulate this problem as the minimization of a conditional KL divergence. Compared to traditional maximum likelihood estimation, our algorithm is prior-free and likelihood-free, meaning that we do not need to impose any prior on the original signals or any observational model, which often restricts the model's flexibility. To tackle the KL divergence minimization problem, we propose a sequential algorithm that reduces the KL divergence and learns an optimal de-mixing flow model at each iteration. This approach completely avoids the unstable adversarial training, a common issue in minimizing the KL divergence. Experiments on toy and real-world datasets show the effectiveness of our method.

翻译：我们研究了利用非线性独立成分分析（ICA）从数据中学习解耦信号的问题。受自监督学习进展的启发，我们提出学习自足信号：恢复出的信号应能够仅依赖其自身所有剩余分量重构缺失值，而无需借助其他任何信号。我们将该问题形式化为条件KL散度的最小化。与传统的最大似然估计相比，我们的算法无需先验且不依赖似然函数，这意味着我们无需对原始信号施加任何先验假设或观测模型，这些限制常会约束模型的灵活性。为求解KL散度最小化问题，我们提出一种序列算法，该算法在每次迭代中降低KL散度并学习最优解混流模型。此方法完全避免了在最小化KL散度时常见的不稳定对抗训练问题。在仿真和真实数据集上的实验验证了我们方法的有效性。