New Publications and Lectures
- New Journal Paper in preparation: E. Riegler, A. Bühler, Yang Pan, and Helmut Bölcskei, Generating Rectifialbe Measures through Neural Networks, arXiv:2412.05109 [cs.LG].
- Journal Paper submitted to Sampling Theory, Signal Processing, and Data Analysis: E Riegler, G. Koliander, D. Stotz, and H. Bölcskei, Completion of Matrices with Low Description Complexit, arXiv:2303.03731 [cs.IT].
- Journal Paper accepted at Information and Inference: A Journal of the IMA: E Riegler, G. Koliander, and H. Bölcskei, Lossy Compression of General Random Variabls, arXiv:2111.12312 [math.PR].
- Plenary tutorial at the 2022 IEEE European School of Information Theory.
- Journal Paper submitted to Information and Inference: A Journal of the IMA: E Riegler, G. Koliander, and H. Bölcskei, “Lossy Compression of General Random Variables,” arXiv:2111.12312 [math.PR].
- New Lecture on Learning, Classification, and Compression at the Swiss Federal Institute of Technology Zurich, Switzerland, Feb. 2021–Jun. 2021.
- Journal Paper in IEEE Trans. Inf. Theory: G. Alberti, H. Bölcskei, C. De Lellis, G. Koliander, and E. Riegler, “Lossless Analog Compression,” IEEE Trans. Inf. Theory, vol. 65, no. 11, pp. 7480–7513, Nov. 2019, arXiv:1803.06887 [math.FA].
- Book Chapter in Information-theoretic Methods in Data Science: E. Riegler and H. Bölcskei, “Uncertainty relations and sparse signal recovery,” in Information-theoretic Methods in Data Science, M. Rodrigues and Y. Eldar, Eds., Cambridge University Press, a href="http://arxiv.org/abs/1811.03996" target="_blank">arXiv:1811.03996 [cs.IT].