I will be starting as an assistant professor of CS at Rice University in Fall 2018.

For the academic year 2017-2018, I will join IBM T. Watson Research Center as a Goldstine Fellow.

This year, I’m co-organizing a workshop on non-convex methods at ICML, with title Advances in non-convex analysis and optimization. This is a workshop co-organized with a great team of colleagues:

We are very excited about the set of confirmed invited speakers, which include:

Check our website the tentative schedule. This is our CfP:

We welcome submissions to the workshop in topics of interest which include

  • Novel theory and techniques for analysis of non-convex methods
  • New non-convex algorithms
  • Spectral learning for matrices and tensors
  • Online algorithms and advances in stochastic gradient descent for non-convex optimization
  • Application of non-convex optimization to diverse application domains such as natural language processing, social networks, health informatics, dictionary learning, and biological sequence analysis.

Papers submitted to the workshop should be up to four pages long excluding references and in ICML 2016 format. They should be sent by email to “”. As the review process is not blind, authors can reveal their identity in their submissions. Accepted submissions will be presented as posters.

Open Problems: We also welcome open problems in the general area of non-convex optimization of interest to the ICML community.

Important Dates: Submission deadline: May 1, 2016 Acceptance notification: May 10, 2016

Registration: Please refer to ICML website for registration details as they become available.

The poster dimensions are the same as the ICML standard.

Stay tuned and send the best papers you have on this subject!