We study statistical estimation in a student--teacher setting, where predictions from a pre-trained teacher are used to guide a student model. A standard approach is to train the student to directly match the teacher's outputs, which we refer to as student soft matching (SM). This approach directly propagates any systematic bias or mis-specification present in the teacher, thereby degrading the student's predictions. We propose and analyze an alternative scheme, known as residual-as-teacher (RaT), in which the teacher is used to estimate residuals in the student's predictions. Our analysis shows how the student can thereby emulate a proximal gradient scheme for solving an oracle optimization problem, and this provably reduces the effect of teacher bias. For general student--teacher pairs, we establish non-asymptotic excess risk bounds for any RaT fixed point, along with convergence guarantees for the student-teacher iterative scheme. For kernel-based student--teacher pairs, we prove a sharp separation: the RaT method achieves the minimax-optimal rate, while the SM method incurs constant prediction error for any sample size. Experiments on both synthetic data and ImageNette classification under covariate shift corroborate our theoretical findings.

The authors study the problem of structure learning for Bayesian networks. The conventional methods for this task include the constraint-based methods or the score-based methods which involve optimizing a discrete score function over the set of DAGs with a combinatorial constraint. Unlike the existing approaches, the authors propose formulating the problem as a continuous optimization problem over real matrices, which performs a global search, and can be solved using standard numerical algorithms. The main idea in this work is using a smooth function for expressing an equality constraint to force acyclicity on the estimated structure. The paper is very well written and enjoyable to read.

Causal discovery from observational data is an important but challenging task in many scientific fields. Recently, NOTEARS [Zheng et al., 2018] formulates the causal structure learning problem as a continuous optimization problem using least-square loss with an acyclicity constraint. Though the least-square loss function is well justified under the standard Gaussian noise assumption, it is limited if the assumption does not hold. In this work, we theoretically show that the violation of the Gaussian noise assumption will hinder the causal direction identification, making the causal orientation fully determined by the causal strength as well as the variances of noises in the linear case and the noises of strong non-Gaussianity in the nonlinear case. Consequently, we propose a more general entropy-based loss that is theoretically consistent with the likelihood score under any noise distribution. We run extensive empirical evaluations on both synthetic data and real-world data to validate the effectiveness of the proposed method and show that our method achieves the best in Structure Hamming Distance, False Discovery Rate, and True Positive Rate matrices.