Lab News April 2023 - ICML23, Textbook
ICML 2023 paper! Manifold Learning Textbook Published!
May 4, 2023
Manifold Learning Book finally released
Our long-awaited, much discussed (by us at least), textbook on Manifold Learning and Dimensionality Reduction (Ghojogh et al., 2023) has now been published officially via Springer Nature and the text is now available at Amazon and other fine booksellers {;)}.
The reference and teaching textbook is on the broad topic area of my former PhD student Benyamin Ghojogh’s thesis. Benyamin led the massive effort involved in the completion of this textbook. We’re confident it will be a fantastic resource for students and researchers wanting a wide view of this field but also one built from the ground up from the fundamentals at each step.
These are fundamental tools and concepts for all data analysis and machine learning professionals. So if you’re interested in a deep dive into this important area, and take a look at our book.
ICML Paper Accepted
Bagi, S. S. G., Gharaee, Z., Schulte, O., & Crowley, M. (2023). Generative Causal Representation Learning for Out-of-Distribution Motion Forecasting. Proceedings of the 40th International Conference on Machine Learning (ICML), 202, 31596–31612. https://doi.org/https://proceedings.mlr.press/v202/shirahmad-gale-bagi23a.html
With all the excitement recently in advances in Artificial Intelligence and Machine Learning (AI/ML), especially Generative AI models such as OpenAI’s GPT, there is a huge need for addressing a broader notion of AI that will be needed for use in the real world. Most of these methods can interpolate, predict, generate new patterns from data but they do this by learning correlations between features in the data, and datapoints over time. But there is a huge literature with methods and theory that deal with other kinds of relationships we can use to describe data, such as causality, uncertainty, confidence, and truth.
In this paper (Bagi et al., 2023) we propose a new framework for leveraging causal information to improve robustness of learning in the presence of distribution shift. Empirical results on the pedestrian motion forecasting domain support our theoretical findings. Prof. Crowley will be presenting this world at ICML 2023 in Hawai’i in July 2023. You can read the whole paper on Arxiv right now.