Call for Papers

Description:
The increased variability of acquired data has recently pushed the field of machine learning to extend its scope to non-standard data including for example functional [1,2], distributional [3], graph, or topological data [4,5]. Successful applications span across a wide range of disciplines such as healthcare [6], action recognition from iPod/iPhone accelerometer data [7], causal inference [8], bioinformatics [9,10], cosmology [11,12], acoustic-to-articulatory speech inversion [13], network inference [14], climate research [15], and ecological inference [16].

Leveraging the underlying structure of these non-standard data types often leads to significant boost in prediction accuracy and inference performance. In order to achieve these compelling improvements, however, numerous challenges and questions have to be addressed:
  • choosing an adequate representation of the data,
  • constructing appropriate similarity measures (inner product, norm or metric) on these representations,
  • efficiently exploiting their intrinsic structure such as multi-scale nature or invariances,
  • designing affordable computational schemes (relying e.g., on surrogate losses),
  • understanding the computational-statistical tradeoffs of the resulting algorithms, and
  • exploring novel application domains.
The goal of this workshop is
  • to discuss new theoretical considerations and applications related to learning with non-standard data,
  • to explore future research directions by bringing together practitioners with various domain expertise and algorithmic tools, and theoreticians interested in providing sound methodology,
  • to accelerate the advances of this recent area and application arsenal.
We encourage submissions on a variety of topics, including but not limited to:
  • Novel applications for learning on non-standard objects
  • Learning theory/algorithms on distributions
  • Topological and geometric data analysis
  • Functional data analysis
  • Multi-task learning, structured output prediction, and surrogate losses
  • Vector-valued learning (e.g., operator-valued kernel)
  • Gaussian processes
  • Learning on graphs and networks
  • Group theoretic methods and invariances in learning
  • Learning with non-standard input/output data
  • Large-scale approximations (e.g. sketching, random Fourier features, hashing, Nyström method, inducing point methods), and statistical-computational efficiency tradeoffs. 
Submission:
Papers submitted to the workshop should be up to four pages long (excluding references), in camera-ready format using the NIPS style; no anonymization is required. They should be uploaded (.pdf, up to 5MB) to CMT3, by Oct. 10, 2017 (5pm, Pacific Time). Accepted submissions will be presented as talks or posters.



Format:
The workshop will be a one day workshop and will consist of invited and contributed talks (30-45 min each), a poster session and a panel discussion with a panel formed by invited speakers.



Contact:
If you have any question or comment, feel free to contact us [''nips17learningon (at) gmail (dot) com"].


References
:

[1] Frédéric Ferraty and Philippe Vieu. Nonparametric Functional Data Analysis: Theory and Practice. Springer Series in Statistics, Springer-Verlag, 2006.

[2] Jane-Ling Wang, Jeng-Min Chiou, and Hans-Georg Müller. Review of Functional Data Analysis. Annual Review of Statistics, 3:1-41, 2015.

[3] Barnabás Póczos, Aarti Singh, Alessandro Rinaldo, Larry Wasserman. Distribution-free Distribution Regression. International Conference on AI and Statistics (AISTATS), PMLR 31:507-515, 2013.

[4] Gunnar Carlsson. Topology and data. Bulletin of the American Mathematical Society, 46 (2): 255-308, 2009.

[5] Vitaliy Kurlin. Research blog: http://kurlin.org/blog/.

[6] Jiayu Zhou, Jun Liu, Vaibhav A. Narayan, and Jieping Ye. Modeling disease progression via multi-task learning. NeuroImage, 78:233-248, 2013.

[7] Xu Sun, Hisashi Kashima, and Naonori Ueda. Large-scale personalized human activity recognition using online multitask learning. IEEE Transactions on Knowledge and Data Engine, 25:2551-2563, 2013.

[8] David Lopez-Paz, Krikamol Muandet, Bernhard Schölkopf, and Ilya Tolstikhin. Towards a Learning Theory of Cause-Effect Inference. International Conference on Machine Learning (ICML), PMLR 37:1452-1461, 2015.

[9] Risi Kondor, Horace Pan. The Multiscale Laplacian Graph Kernel. Advances in Neural Information Processing Systems (NIPS), 2982-2990, 2016.

[10] Genki Kusano, Yasuaki Hiraoka, Kenji Fukumizu. Persistence weighted Gaussian kernel for topological data analysis. International Conference on Machine Learning (ICML), PMLR 48:2004-2013, 2016.

[11] Siamak Ravanbakhsh, Junier Oliva, Sebastian Fromenteau, Layne Price, Shirley Ho, Jeff Schneider, Barnabás Póczos. Estimating Cosmological Parameters from the Dark Matter Distribution. International Conference on Machine Learning (ICML), PMLR 48:2407-2416, 2016.

[12] Ho Chung Leon Law, Dougal J. Sutherland, Dino Sejdinovic, Seth Flaxman. Bayesian Distribution Regression. Technical Report, 2017.

[13] Hachem Kadri, Emmanuel Duflos, Philippe Preux, Stéphane Canu, Alain Rakotomamonjy, and Julien Audiffren. Operator-valued kernels for learning from functional response data. Journal of Machine Learning Research, 17:1-54, 2016.

[14] Céline Brouard, Marie Szafranski, and Florence d’Alché-Buc. Input output kernel regression: Supervised and semi-supervised structured output prediction with operator-valued kernels. Journal of Machine Learning Research, 17:1-48, 2016.

[15] Zoltán Szabó, Bharath K. Sriperumbudur, Barnabás Póczos, Arthur Gretton. Learning Theory for Distribution Regression. Journal of Machine Learning Research, 17(152):1-40, 2016.

[16] Seth Flaxman, Yu-Xiang Wang, and Alex Smola. Who supported Obama in 2012? Ecological inference through distribution regression. In ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 289-298, 2015.