Mapping the Energy Landscape of Non-convex Optimization Problems
An energy landscape map (ELM) characterizes and visualizes an energy function with a tree structure, in which each leaf node represents a local minimum and each non-leaf node represents the barrier between adjacent energy basins. We demonstrate the utility of ELMs in analyzing non-convex energy minimization problems with two case studies: clustering with Gaussian mixture models and learning mixtures of Bernoulli templates from images. By plotting the ELMs, we are able to visualize the impact of different problem settings on the energy landscape as well as to examine and compare the behaviors of different learning algorithms on the ELMs.
KeywordsLocal Minimum Leaf Node Gaussian Mixture Model Energy Landscape Hypothesis Space
Unable to display preview. Download preview PDF.
- 3.Blake, C.L., Merz, C.J.: UCI repository of machine learning databases (1998)Google Scholar
- 4.Dasgupta, S., Schulman, L.J.: A two-round variant of em for gaussian mixtures. In: Proceedings of the Sixteenth Conference on Uncertainty in Artificial Intelligence, UAI 2000, pp. 152–159. Morgan Kaufmann Publishers Inc., San Francisco (2000)Google Scholar
- 8.Pavlovskaia, M., Tu, K., Zhu, S.C.: Mapping energy landscapes of non-convex learning problems. arXiv preprint arXiv:1410.0576 (2014)Google Scholar
- 10.Samdani, R., Chang, M.W., Roth, D.: Unified expectation maximization. In: Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 688–698. Association for Computational Linguistics (2012)Google Scholar
- 12.Tu, K., Honavar, V.: Unambiguity regularization for unsupervised learning of probabilistic grammars. In: Proceedings of the 2012 Conference on Empirical Methods in Natural Language Processing and Natural Language Learning, EMNLP-CoNLL 2012 (2012)Google Scholar