Miguel Á. Carreira-Perpiñán Professor Dept. of Computer Science and Engineering School of Engineering University of California, Merced 5200 N. Lake Road Merced, CA 95343 Office: SE2-217, lab: SE2-213B Email: mcarreira-perpinan [at] ucmerced.edu WWW: http://faculty.ucmerced.edu/mcarreira-perpinan Directions for visitors

I am not looking for winter/summer interns or short-term (e.g. 1 year) students.

Research interests

My basic research interests are in machine learning. In recent years, I have been working on topics in the intersection of optimisation and machine learning, in particular in learning algorithms for deep neural nets and other "nested" systems, for decision trees and tree-based models, and for nonlinear embeddings; and algorithms for optimally compressing deep neural nets. Other topics of interest are dimensionality reduction/manifold learning, clustering, denoising and other unsupervised learning problems, and mean-shift algorithms. I often get inspiration from problems in speech processing (e.g. articulatory inversion and model adaptation), computer vision (e.g. segmentation, articulated pose tracking, image registration), sensor networks, robotics (e.g. inverse kinematics) and other application areas. In the past, I also worked on computational neuroscience, specifically on dimension reduction models of the maps of the visual cortex.

• Curriculum Vitae and biography
• Personal information
• Papers
• Software and databases
• Research, in particular:
  • The tree alternating optimisation (TAO) algorithm for learning decision trees and tree-based models.
    Cubist art using TAO.
  • The learning-compression (LC) algorithm for finding optimally compressed neural networks.
  • The method of auxiliary coordinates (MAC) for optimising deeply nested systems.
• Teaching
• PhD students:
  • Magzhan Gabidolla, PhD EECS
  • Kuat Gazizov, PhD EECS
  • Rasul Kairgeldin, PhD EECS
• Past PhD students:
  • Arman Zharmagambetov, PhD EECS 2022.
    First position: postdoctoral fellow, Fundamental AI Research (FAIR), Meta AI. Currently: research scientist at Fundamental AI Research (FAIR), Meta AI.
  • Suryabhan Singh Hada, PhD EECS 2022.
    First position: AI engineer at LinkedIn.
  • Yerlan Idelbayev, PhD EECS 2021.
    First position: applied scientist at Amazon. Currently: ML engineer at Snap Inc.
  • Max Vladymyrov, PhD EECS 2014.
    First position: research scientist at Yahoo Labs. Currently: senior research scientist at Google DeepMind.
  • Weiran Wang, PhD EECS 2013.
    First position: postdoc at TTI-Chicago. Currently: assistant professor at the University of Iowa.
  • Ankur Kamthe, PhD EECS 2012 (co-advisor).
    First position: software engineer at Aruba Networks.
  • Chao Qin, PhD EECS 2011.
    First position: research scientist at sharethis.com. Currently: staff software engineer at Google.
• Current professional service:
  • Area chair, Int. Conf. Learning Representations (ICLR 2025).
  • Senior area chair, AAAI Conf. Artificial Intelligence (AAAI 2025).
  • Area chair, Annual Conference on Neural Information Processing Systems (NeurIPS 2024).
  • Action editor (since 2017), J. Machine Learning Research (JMLR).
• Current funding:
  • NSF: "The TAO algorithm: principled, efficient optimization of decision trees, forests, tree-based neural nets, and beyond", $425,000 (2020-2025).

UC Merced | EECS | MACP's Home Page