eprintid: 10198390 rev_number: 8 eprint_status: archive userid: 699 dir: disk0/10/19/83/90 datestamp: 2024-10-14 14:57:57 lastmod: 2024-10-14 14:57:57 status_changed: 2024-10-14 14:57:57 type: proceedings_section metadata_visibility: show sword_depositor: 699 creators_name: Song, Y creators_name: Wan, K creators_name: Liao, Z creators_name: Xu, H creators_name: Caire, G creators_name: Shamai, S title: An Achievable and Analytic Solution to Information Bottleneck for Gaussian Mixtures ispublished: pub divisions: UCL divisions: B04 divisions: F46 keywords: Quantization (signal), Closed-form solutions, AWGN, Phase modulation, Source coding, Approximation algorithms, Binary phase shift keying note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. abstract: In this paper, we consider a remote source coding problem with binary phase shift keying (BPSK) modulation sources, where observations are corrupted by additive white Gaussian noise (AWGN). An intermediate node, such as a relay, receives these observations and performs further compression to find the optimal trade-off between complexity and relevance. This problem can be formulated as an information bottleneck (IB) problem with Bernoulli sources and Gaussian mixture observations, for which no closed-form solution is known. To address this challenge, we propose a unified achievable scheme that employs three different compression strategies for intermediate node processing, i.e., two-level quantization, multi-level deterministic quantization, and soft quantization with tanh function. Comparative analyses with existing methods, such as the Blahut-Arimoto (BA) algorithm and the Information Dropout approach, are performed through numerical evaluations. The proposed analytic scheme is observed to consistently approach the (numerically) optimal performance over a range of signal-to-noise ratios (SNRs), confirming its effectiveness in the considered setting. date: 2024-08-19 date_type: published publisher: IEEE official_url: https://doi.org/10.1109/ISIT57864.2024.10619077 oa_status: green full_text_type: other language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 2313001 doi: 10.1109/ISIT57864.2024.10619077 lyricists_name: Xu, Hao lyricists_id: HXUCX90 actors_name: Xu, Hao actors_id: HXUCX90 actors_role: owner full_text_status: public pres_type: paper publication: IEEE International Symposium on Information Theory - Proceedings place_of_pub: Athens, Greece pagerange: 2460-2465 event_title: 2024 IEEE International Symposium on Information Theory (ISIT) event_dates: 7 Jul 2024 - 12 Jul 2024 issn: 2157-8095 book_title: IEEE International Symposium on Information Theory - Proceedings citation: Song, Y; Wan, K; Liao, Z; Xu, H; Caire, G; Shamai, S; (2024) An Achievable and Analytic Solution to Information Bottleneck for Gaussian Mixtures. In: IEEE International Symposium on Information Theory - Proceedings. (pp. pp. 2460-2465). IEEE: Athens, Greece. Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10198390/1/ISIT_2023-YI_version_final_submission.pdf