Shang Wu

Shunyao Zhang, Yonggan Fu, Shang Wu et al.

Boosting the task accuracy of tiny neural networks (TNNs) has become a fundamental challenge for enabling the deployments of TNNs on edge devices which are constrained by strict limitations in terms of memory, computation, bandwidth, and power supply. To this end, we propose a framework called NetDistiller to boost the achievable accuracy of TNNs by treating them as sub-networks of a weight-sharing teacher constructed by expanding the number of channels of the TNN. Specifically, the target TNN model is jointly trained with the weight-sharing teacher model via (1) gradient surgery to tackle the gradient conflicts between them and (2) uncertainty-aware distillation to mitigate the overfitting of the teacher model. Extensive experiments across diverse tasks validate NetDistiller's effectiveness in boosting TNNs' achievable accuracy over state-of-the-art methods. Our code is available at https://github.com/GATECH-EIC/NetDistiller.

Shang Wu, Yazhen Wang

The seminal paper of Jordan, Kinderlehrer, and Otto introduced what is now widely known as the JKO scheme, an iterative algorithmic framework for computing distributions. This scheme can be interpreted as a Wasserstein gradient flow and has been successfully applied in machine learning contexts, such as deriving policy solutions in reinforcement learning. In this paper, we extend the JKO scheme to accommodate models with unknown parameters. Specifically, we develop statistical methods to estimate these parameters and adapt the JKO scheme to incorporate the estimated values. To analyze the adopted statistical JKO scheme, we establish an asymptotic theory via stochastic partial differential equations that describes its limiting dynamic behavior. Our framework allows both the sample size used in parameter estimation and the number of algorithmic iterations to go to infinity. This study offers a unified framework for joint computational and statistical asymptotic analysis of the statistical JKO scheme. On the computational side, we examine the scheme's dynamic behavior as the number of iterations increases, while on the statistical side, we investigate the large-sample behavior of the resulting distributions computed through the scheme. We conduct numerical simulations to evaluate the finite-sample performance of the proposed methods and validate the developed asymptotic theory.