More Like this

1. Folding points to a point and lines to a line

   Akitaya, Hugo A.; Ballinger, Brad; Demaine, Erik D.; Hull, Thomas C.; Schmidt, Christiane (August 2021, Proceedings of the 33rd Canadian Conference on Computational Geometry (CCCG 2021))

   He, Meng; Sheehy, Don (Ed.)

   We introduce basic, but heretofore generally unexplored, problems in computational origami that are similar in style to classic problems from discrete and computational geometry. We consider the problems of folding each corner of a polygon P to a point p and folding each edge of a polygon P onto a line segment L that connects two boundary points of P and compute the number of edges of the polygon containing p or L limited by crease lines and boundary edges. 

   more » « less
2. Learning to Optimize: A Primer and A Benchmark

   Chen, Tianlong; Chen, Xiaohan; Chen, Wuyang; Heaton, Howard; Liu, Jialin; Wang, Zhangyang; Yin, Wotao (June 2022, Journal of machine learning research)

   David Wipf (Ed.)

   Learning to optimize (L2O) is an emerging approach that leverages machine learning to develop optimization methods, aiming at reducing the laborious iterations of hand engineering. It automates the design of an optimization method based on its performance on a set of training problems. This data-driven procedure generates methods that can efficiently solve problems similar to those in training. In sharp contrast, the typical and traditional designs of optimization methods are theory-driven, so they obtain performance guarantees over the classes of problems specified by the theory. The difference makes L2O suitable for repeatedly solving a particular optimization problem over a specific distribution of data, while it typically fails on out-of-distribution problems. The practicality of L2O depends on the type of target optimization, the chosen architecture of the method to learn, and the training procedure. This new paradigm has motivated a community of researchers to explore L2O and report their findings. This article is poised to be the first comprehensive survey and benchmark of L2O for continuous optimization. We set up taxonomies, categorize existing works and research directions, present insights, and identify open challenges. We benchmarked many existing L2O approaches on a few representative optimization problems. For reproducible research and fair benchmarking purposes, we released our software implementation and data in the package Open-L2O at https://github.com/VITA-Group/Open-L2O. 

   more » « less
3. A comparative approach to affect and cooperation

   https://doi.org/10.1016/j.neubiorev.2019.09.027  

   Massen, Jorg J.M.; Behrens, Friederike; Martin, Jordan S.; Stocker, Martina; Brosnan, Sarah F. (December 2019, Neuroscience & Biobehavioral Reviews)
4. Learning to Factorize and Relight a City

   https://doi.org/10.1007/978-3-030-58548-8_32  

   Liu, Andrew; Ginosar, Shiry; Zhou, Tinghui; Efros, Alexei; Snavely, Noah (October 2020, Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science)
5. A systems approach to perception and action

   https://doi.org/https://doi.org/10.1080/10407413.2017.1330119  

   Amazeen, P. G.; Amazeen, E. L. (January 2017, Ecological psychology)