Affiliation:
1. School of Computer Science and Engineering, The Hebrew University of Jerusalem, Jerusalem 9190401, Israel
Abstract
The Information Bottleneck (IB) is a method of lossy compression of relevant information. Its rate-distortion (RD) curve describes the fundamental tradeoff between input compression and the preservation of relevant information embedded in the input. However, it conceals the underlying dynamics of optimal input encodings. We argue that these typically follow a piecewise smooth trajectory when input information is being compressed, as recently shown in RD. These smooth dynamics are interrupted when an optimal encoding changes qualitatively, at a bifurcation. By leveraging the IB’s intimate relations with RD, we provide substantial insights into its solution structure, highlighting caveats in its finite-dimensional treatments. Sub-optimal solutions are seen to collide or exchange optimality at its bifurcations. Despite the acceptance of the IB and its applications, there are surprisingly few techniques to solve it numerically, even for finite problems whose distribution is known. We derive anew the IB’s first-order Ordinary Differential Equation, which describes the dynamics underlying its optimal tradeoff curve. To exploit these dynamics, we not only detect IB bifurcations but also identify their type in order to handle them accordingly. Rather than approaching the IB’s optimal tradeoff curve from sub-optimal directions, the latter allows us to follow a solution’s trajectory along the optimal curve under mild assumptions. We thereby translate an understanding of IB bifurcations into a surprisingly accurate numerical algorithm.
Funder
Israel Science Foundation
Subject
General Physics and Astronomy
Reference40 articles.
1. Tishby, N., Pereira, F.C., and Bialek, W. (1999, January 22–24). The Information Bottleneck Method. Proceedings of the 37th Annual Allerton Conference on Communication, Control, and Computing, Monticello, IL, USA.
2. A Conditional Entropy Bound for a Pair of Discrete Random Variables;Witsenhausen;IEEE Trans. Inf. Theory,1975
3. Zaidi, A., Estella-Aguerri, I., and Shamai, S. (2020). On the Information Bottleneck Problems: Models, connections, Applications and Information Theoretic Views. Entropy, 22.
4. Agmon, S., Benger, E., Ordentlich, O., and Tishby, N. (2021, January 12–20). Critical Slowing Down Near Topological Transitions in Rate-Distortion Problems. Proceedings of the 2021 IEEE International Symposium on Information Theory (ISIT), Melbourne, Australia.
5. Gilad-Bachrach, R., Navot, A., and Tishby, N. (2003). Learning Theory and Kernel Machines, Springer.