A predictor, $f_A : X \to Y$, learned with data from a source domain (A) might not be accurate on a target domain (B) when their distributions are different. Domain adaptation aims to reduce the negative effects of this distribution mismatch. Here, we analyze the case where $P_A(Y\ |\ X) \neq P_B(Y\ |\ X)$, $P_A(X) \neq P_B(X)$ but $P_A(Y) = P_B(Y)$; where there are affine transformations of $X$ that makes all distributions equivalent. We propose an approach to project the source and target domains into a lower-dimensional, common space, by (1) projecting the domains into the eigenvectors of the empirical covariance matrices of each domain, then (2) finding an orthogonal matrix that minimizes the maximum mean discrepancy between the projections of both domains. For arbitrary affine transformations, there is an inherent unidentifiability problem when performing unsupervised domain adaptation that can be alleviated in the semi-supervised case. We show the effectiveness of our approach in simulated data and in binary digit classification tasks, obtaining improvements up to 48% accuracy when correcting for the domain shift in the data.
翻译:预测器 $f_ A : $_ A : X\ to Y$ : 以源域( A) 获得的数据在分布不同时, 目标域( B) 可能不准确 。 域适应的目的是减少这种分布不匹配的负面效应 。 在此, 我们分析一个案例 : $P_ A( Y\ Q )\ neq P_ B( Y ) $ ) 、 $P_ A( A)\ \ neq P_ B( X) $, 但 $P_ B( Y) = P_ B( Y) $ ; 目标域( B) 存在折叠式转换, 使所有分布都相等 。 我们建议了一种方法, 将源和目标域投射到一个较低维度的共同空间。 我们分析域域域域域的预测器将域投射到每个域的经验变量矩阵的精度上, 然后找到一个可以将两个域预测的最大平均值差异最小化的矩阵矩阵。 对于任意的转换, 当进行非超固化域域域调整时, 我们的校正的校正的校正了48 时, 的校正的校正的校正的校正的校正的校正的校正的校正的校正的校正的校正的校正的校正的校正中的数据。