Upcoming Seminars
June 28
NO SEMINAR
July 3
Special Wednesday Seminar
Learning-augmented algorithms for online optimization and beyond
Nico Christianson, PhD candidate in Computing and Mathematical Sciences at Caltech
Abstract:
Modern AI and ML algorithms can deliver transformative performance improvements for decision-making under uncertainty, where traditional, worst-case algorithms are often too conservative. However, AI and ML lack worst-case guarantees, hindering their deployment to real-world settings like energy systems where safety and reliability are critical. In this talk, I will discuss work on developing machine-learning augmented algorithms with provable performance guarantees, focusing in particular on algorithms and lower bounds for integrating black-box ML “advice” in general online optimization problems. I will also highlight some recent steps toward leveraging uncertainty quantification to improve learning-augmented algorithm performance, as well as applications of our work to energy and sustainable computing.
Presenter Bio:
Nico Christianson is a PhD candidate in Computing and Mathematical Sciences at Caltech, where he is advised by Adam Wierman and Steven Low. Before Caltech, he received his AB in Applied Mathematics from Harvard. He is broadly interested in online algorithms, learning, and optimization, with an emphasis on developing learning-augmented algorithms with provable guarantees for problems spanning energy, carbon-aware computing, and sustainability. Nico’s work is supported by an NSF Graduate Research Fellowship.
Add event to calendar
July 5
Join the journey towards Responsible AI
Katrina Ingram, Ethically Aligned AI
Co-hosted by Technology Alberta
Abstract:
If you're not building responsible AI, what kind of AI are you building? In this provocative session, Katrina Ingram will share her journey from U of A student to entrepreneurial pioneer in the field Responsible AI. She'll cover core issues around ethics, data, privacy and algorithmic bias, as well as bigger societal concerns around the impacts of AI on our work and life. This talk will cover a range of perspectives and offer advice for developers, organizations and end users. It will also touch on some exciting new career opportunities in the field of Responsible AI, including the emerging area of AI audits.
Presenter Bio:
Katrina Ingram is the Founder and CEO of Ethically Aligned AI, a company focused on helping organizations to drive better outcomes in the design, development and deployment of AI systems. A seasoned executive, Katrina has over two decades of experience running both not for profit and corporate organizations in the technology and media sectors as well as experience in the public sector. She is a member of DAMA (data management professionals) and volunteers with several AI ethics organizations. She was named to the 100 Brilliant Women in AI Ethics list. Katrina holds an undergrad in business administration from Simon Fraser University, a master of arts in communications and technology from the University of Alberta and is an IAPP certified information privacy professional (CIPP/C). She combines her love of audio and interest in AI as the host of the podcast, AI4Society Dialogues. Katrina developed Canada's first micro-credential in AI Ethics in partnership with Athabasca University. She currently teaches at the University of Alberta and MacEwan University as a sessional instructor. She is a member of the Calgary Police Services Technology Ethics Committee and recently served as the City of Edmonton's Data Ethics Advisor.
Add event to calendar
July 12
Learning Continually by Spectral Regularization
Alex Lewandowski, PhD student, University of Alberta
Abstract:
Neural networks can become less trainable over the course of learning, a phenomenon referred to as loss of plasticity. This talk will describe a spectral perspective on neural network trainability. At initialization, the distribution of singular values for the neural network parameters is relatively uniform. Over the course of learning, the maximum singular value (spectral norm) grows with the number of updates performed by the learning algorithm. We propose spectral regularization, which regularizes the spectral norm, to maintain the spectral properties present at initialization. Our experiments across a wide variety of datasets, architectures and non-stationarities demonstrate that spectral regularization is both effective and insensitive to hyperparameters.
Presenter Bio:
Alex Lewandowski is a PhD student supervised by Dale Schuurmans and Marlos C. Machado at the University of Alberta. His research interest is in understanding scalable continual learning algorithms, with the goal of developing algorithms capable of learning autonomously at every scale.
Add event to calendar
July 19
Title TBA
Speaker TBA
Abstract:
TBA
Presenter Bio:
TBA
Calendar links coming soon!
July 26
Title TBA
José Miguel Aragón Jurado
NOTE: LOCATION CHANGE - CSC B-10
Abstract:
TBA
Presenter Bio:
TBA
Calendar links coming soon!
July 29
Special Monday Seminar
Title TBA
Dr. Kris Shrishak, Senior Fellow at the Irish Council for Civil Liberties
NOTE: LOCATION CHANGE - CSC B-10
Abstract:
TBA
Presenter Bio:
TBA
Calendar links coming soon!
August 2
Title TBA
Speaker TBA
Co-hosted by Technology Alberta
NOTE: LOCATION CHANGE - CSC B-10
Abstract:
TBA
Presenter Bio:
TBA
Calendar links coming soon!
August 9
Title TBA
Speaker TBA
NOTE: LOCATION CHANGE - CSC B-10
Abstract:
TBA
Presenter Bio:
TBA
Calendar links coming soon!
August 16
Title TBA
Vlad Tkachuk, PhD student, University of Alberta
NOTE: LOCATION CHANGE - CSC B-10
Abstract:
TBA
Presenter Bio:
TBA
Calendar links coming soon!
August 23
Title TBA
Speaker TBA
NOTE: LOCATION CHANGE - CSC B-10
Abstract:
TBA
Presenter Bio:
TBA
Calendar links coming soon!
August 30
Title TBA
Yuqiao Wen, PhD student, University of Alberta
Abstract:
TBA
Presenter Bio:
TBA
Calendar links coming soon!
More dates coming soon!