Department of Mathematics
 Search | Help | Login | pdf version | printable version

Math @ Duke



Publications [#343525] of Robert Calderbank

Papers Published

  1. Nguyen, DM; Tsiligianni, E; Calderbank, R; Deligiannis, N, Regularizing autoencoder-based matrix completion models via manifold learning, European Signal Processing Conference, vol. 2018-September (November, 2018), pp. 1880-1884, ISBN 9789082797015 [doi]
    (last updated on 2019/07/18)

    © EURASIP 2018. Autoencoders are popular among neural-network-based matrix completion models due to their ability to retrieve potential latent factors from the partially observed matrices. Nevertheless, when training data is scarce their performance is significantly degraded due to overfitting. In this paper, we mitigate overfitting with a data-dependent regularization technique that relies on the principles of multi-task learning. Specifically, we propose an autoencoder-based matrix completion model that performs prediction of the unknown matrix values as a main task, and manifold learning as an auxiliary task. The latter acts as an inductive bias, leading to solutions that generalize better. The proposed model outperforms the existing autoencoder-based models designed for matrix completion, achieving high reconstruction accuracy in well-known datasets.
ph: 919.660.2800
fax: 919.660.2821

Mathematics Department
Duke University, Box 90320
Durham, NC 27708-0320