Mediated Uncoupled Learning: Learning Functions without Direct Input-output Correspondences

07/16/2021
by   Ikko Yamane, et al.
0

Ordinary supervised learning is useful when we have paired training data of input X and output Y. However, such paired data can be difficult to collect in practice. In this paper, we consider the task of predicting Y from X when we have no paired data of them, but we have two separate, independent datasets of X and Y each observed with some mediating variable U, that is, we have two datasets S_X = {(X_i, U_i)} and S_Y = {(U'_j, Y'_j)}. A naive approach is to predict U from X using S_X and then Y from U using S_Y, but we show that this is not statistically consistent. Moreover, predicting U can be more difficult than predicting Y in practice, e.g., when U has higher dimensionality. To circumvent the difficulty, we propose a new method that avoids predicting U but directly learns Y = f(X) by training f(X) with S_X to predict h(U) which is trained with S_Y to approximate Y. We prove statistical consistency and error bounds of our method and experimentally confirm its practical usefulness.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset