NIPS 2012 Workshop: Perturbations, Optimization, and Statistics

Workshop in conjunction with NIPS 2012.
Saturday, December 8, 2012, Lake Tahoe, Nevada, United States.

Location: Glenbrook + Emerald Bay, Harrah's Special Events Center 2nd Floor.
Schedule: Check out the workshop's program here.


In nearly all machine learning tasks, we expect there to be randomness, or noise, in the data we observe and in the relationships encoded by the model. Usually, this noise is considered undesirable, and we would eliminate it if possible. However, there is an emerging body of work on perturbation methods, showing the benefits of explicitly adding noise into the modeling, learning, and inference pipelines. This workshop will bring together the growing community of researchers interested in different aspects of this area, and will broaden our understanding of why and how perturbation methods can be useful.

More generally, perturbation methods usually provide efficient and principled ways to reason about the neighborhood of possible outcomes when trying to make the best decision. For example, some might want to arrive at the best outcome that is robust to small changes in model parameters. Others might want to find the best choice while compensating for their lack of knowledge by averaging over the different outcomes. Recently, several works influenced by diverse fields of research such as statistics, optimization, machine learning, and theoretical computer science, use perturbation methods in similar ways. The goal of this workshop is to explore different techniques in perturbation methods and their consequences on computation, statistics and optimization. We shall specifically be interested in understanding the following issues:

  • Statistical Modeling: What types of statistical models can be defined for structured prediction? How can random perturbations be used to relate computation and statistics?

  • Efficient Sampling: What are the computational properties that allow efficient and unbiased sampling? How do perturbations control the geometry of such models and how can we construct sampling methods for these families?

  • Approximate Inference: What are the computational and statistical requirements from inference? How can the maximum of random perturbations be used to measure the uncertainty of a system?

  • Learning: How can we probabilistically learn model parameters from training data using random perturbations? What are the connections with max-margin and conditional random fields techniques?

  • Theory: How does the maximum of a random process relate to its complexity? What are the statistical and computational properties it describes in Gaussian free fields over graphs?

  • Pseudo-sampling: How do dynamical systems encode randomness? To what extent do perturbations direct us to the “pseudo-randomness” of its underlying dynamics?

  • Robust classification: How can classifiers be learned in a robust way, and how can support vector machines be realized in this context? What are the relations between adversarial perturbations and regularizations and what are their extensions to structured predictions?

  • Robust reconstructions: How can information be robustly encoded? In what ways can learning be improved by perturbing the input measurements?

  • Adversarial Uncertainty: How can structured prediction be performed in zero-sum game setting? What are the computational qualities of such solutions, and do Nash-equilibria exists in these cases?

Target Audience: The workshop should appeal to NIPS attendees interested in both theoretical aspects such as Bayesian modeling, Monte Carlo sampling, optimization, inference, and learning, as well as practical applications in computer vision and language modeling.

Call for Papers

In addition to a program of invited presentations, we solicit contribution of short papers that explore perturbation-based methods in the context of topics such as: statistical modeling, sampling, inference, estimation, theory, robust optimization, robust learning. We are interested in both theoretical and application-oriented works. We also welcome papers that explore connections between alternative ways of using perturbations.

Contributed papers should adhere to the NIPS format and are encouraged to be up to four pages long (without counting the list of references). Papers submitted for review do not need to be anonymized. There will be no official proceedings. Thus, apart from papers reporting novel unpublished work, we also welcome submissions describing work in progress or summarizing a longer paper under review for a journal or conference (this should be clearly stated though). Accepted papers will be presented as posters; some may also be selected for spotlight talks.

Please submit papers in PDF format by email to The submission deadline has been extended to October 19, 2012 and notifications of acceptance will be sent by October 28, 2012. At least one of the authors must be attending the workshop to present the work.

You can also download the Call for Papers in PDF or TXT.

Confirmed Invited Speakers



We have assembled below a list of indicative references related to the workshop's theme.

Machine learning

Extreme value statistics

Discrete choice in psychology and economics

Mathematics and statistical physics