In some causal inference scenarios, the treatment (i.e. cause) variable is
measured inaccurately, for instance in epidemiology or econometrics. Failure to
correct for the effect of this measurement error can lead to biased causal
effect estimates. Previous research has not studied methods that address this
issue from a causal viewpoint while allowing for complex nonlinear dependencies
and without assuming access to side information. For such as scenario, this
paper proposes a model that assumes a continuous treatment variable which is
inaccurately measured. Building on existing results for measurement error
models, we prove that our model's causal effect estimates are identifiable,
even without knowledge of the measurement error variance or other side
information. Our method relies on a deep latent variable model where Gaussian
conditionals are parameterized by neural networks, and we develop an amortized
importance-weighted variational objective for training the model. Empirical
results demonstrate the method's good performance with unknown measurement
error. More broadly, our work extends the range of applications where reliable
causal inference can be conducted.

本文提出了一种基于深层潜在变量模型和重要性加权变分目标的测量误差下因果推断的方法，使得即使没有测量误差方差和侧面信息，也可以得出可靠的因果效应估计。

带噪声治疗和无附带信息可辨识的因果推断

Identifiable causal inference with noisy treatment and no side  information

Given the ubiquity of deep neural networks, it is important that these models
do not reveal information about sensitive data that they have been trained on.
In model inversion attacks, a malicious user attempts to recover the private
dataset used to train a supervised neural network. A successful model inversion
attack should generate realistic and diverse samples that accurately describe
each of the classes in the private dataset. In this work, we provide a
probabilistic interpretation of model inversion attacks, and formulate a
variational objective that accounts for both diversity and accuracy. In order
to optimize this variational objective, we choose a variational family defined
in the code space of a deep generative model, trained on a public auxiliary
dataset that shares some structural similarity with the target dataset.
Empirically, our method substantially improves performance in terms of target
attack accuracy, sample realism, and diversity on datasets of faces and chest
X-ray images.

本研究提供了深度学习中一种重要的隐私保护策略，即基于变分自编码器和生成模型的攻击方法，可以更加准确地生成包含敏感数据的样本，并保持样本的多样性和真实性。

变分模型反演攻击

Variational Model Inversion Attacks

Dropout, a stochastic regularisation technique for training of neural
networks, has recently been reinterpreted as a specific type of approximate
inference algorithm for Bayesian neural networks. The main contribution of the
reinterpretation is in providing a theoretical framework useful for analysing
and extending the algorithm. We show that the proposed framework suffers from
several issues; from undefined or pathological behaviour of the true posterior
related to use of improper priors, to an ill-defined variational objective due
to singularity of the approximating distribution relative to the true
posterior. Our analysis of the improper log uniform prior used in variational
Gaussian dropout suggests the pathologies are generally irredeemable, and that
the algorithm still works only because the variational formulation annuls some
of the pathologies. To address the singularity issue, we proffer Quasi-KL (QKL)
divergence, a new approximate inference objective for approximation of
high-dimensional distributions. We show that motivations for variational
Bernoulli dropout based on discretisation and noise have QKL as a limit.
Properties of QKL are studied both theoretically and on a simple practical
example which shows that the QKL-optimal approximation of a full rank Gaussian
with a degenerate one naturally leads to the Principal Component Analysis
solution.

将 Dropout 重新解释为贝叶斯神经网络的近似推理算法，提出了一个有用的理论框架，但对于使用不当的先验概率，存在未定义或病态行为的真后验分布问题；对于近似分布相对于真后验分布的奇异性而言，近似难以定义。为了解决这些问题，提出了 Quasi-KL（QKL）差异作为新的近似推理目标。