Mila organizes weekly tea talks generally on Friday at 10:30 in the auditorium. These talks are technical presentations aimed at the level of Mila researchers on a variety of subjects spanning machine learning and are open to the public.
If you’re interested in giving a tea talk, please email .
If you’d like to subscribe to our mailing lists and get notified of all upcoming talks, please email
The schedule for previous and upcoming talks as well as some of the presentation slides are available below.
|Fri 10 January||10h30||Amin Emad||McGill||Mila Agora||On the road to individualized medicine: machine learning in the era of ‘omics’ data||Individualized medicine (IM) promises to revolutionize patient care by providing personalized treatments based on an individual’s molecular and clinical characteristics. However, we are still far from achieving the goals of IM. For example, in the case of cancer which is the leading cause of death in Canada, the majority of patients only receive (often inadequate) ‘standard of care’ treatment for their cancer type, independent of their tumours’ unique molecular profile. Even when a patient is originally responsive to a drug, they may develop drug resistance and thus face a relapse of cancer. Predicting the patients’ clinical drug response to different treatments and identifying biomarkers of drug sensitivity that can be targeted to overcome drug resistance are two major challenges in moving towards individualized medicine. Machine learning (ML) methods are a natural solution to address these issues, however the complexity of the underlying biological mechanisms and the unique characteristics of the heterogeneous, high-dimensional, multi-modal, and noisy data prohibits us from using off-the-shelf ML algorithms. In this talk, I will describe some recent approaches we developed to address these issues and will describe some important remaining challenges in this domain and our plans to address them.||Dr. Emad is an Assistant Professor of Electrical and Computer Engineering at McGill University, leading the Computational Biology and Artificial Intelligence (COMBINE) lab. He is affiliated with McGill's Quantitative Life Sciences (QLS) program and McGill Initiative in Computational Medicine (MiCM), and is affiliated with the National Center for Supercomputing Applications at the University of Illinois (UIUC). Before joining McGill, he was a Postdoctoral Research Associate at the NIH KnowEnG Center of Excellence in Big Data Computing associated with the Department of Computer Science and the Institute for Genomic Biology (IGB) at UIUC. He received his PhD from UIUC in 2015, his MSc from the University of Alberta in 2009 and his BSc from Sharif University of Technology in 2007. His current research interests include developing novel computational methods based on machine learning, network representation learning, and statistical methods to study various problems in pharmacogenomics and regulatory systems genomics.|
|Fri 17 January||10h30||Irina Rish||Mila||Mila Agora||Modeling Psychotherapy Dialogues with Kernelized Hashcode Representations: A Nonparametric Information-Theoretic Approach||We propose a novel dialogue modeling framework, the first-ever nonparametric kernel functions based approach for dialogue modeling, which learns kernelized hashcodes as compressed text representations; unlike traditional deep learning models, it handles well relatively small datasets, while also scaling to large ones. We also derive a novel lower bound on mutual information, used as a model-selection criterion favoring representations with better alignment between the utterances of participants in a collaborative dialogue setting, as well as higher predictability of the generated responses. As demonstrated on three real-life datasets, including prominently psychotherapy sessions, the proposed approach significantly outperforms several state-of-art neural network based dialogue systems, both in terms of computational efficiency, reducing training time from days or weeks to hours, and the response quality, achieving an order of magnitude improvement over competitors in frequency of being chosen as the best model by human evaluators.||Irina Rish is an Associate Professor in the Computer Science and Operations Research department at the Université de Montréal (UdeM) and a core member of MILA - Quebec AI Institute. She holds MSc and PhD in AI from University of California, Irvine and MSc in Applied Mathematics from Moscow Gubkin Institute. Dr. Rish's research focus is on machine learning, neural data analysis and neuroscience-inspired AI. |
Her current research interests include continual lifelong learning, optimization algorithms for deep neural networks, sparse modeling and probabilistic inference, dialog generation, biologically plausible reinforcement learning, and dynamical systems approaches to brain imaging analysis. Before joining UdeM and MILA in 2019, Irina was a research scientist at the IBM T.J. Watson Research Center, where she worked on various projects at the intersection of neuroscience and AI, and led the Neuro-AI challenge. She received multiple IBM awards, including IBM Eminence & Excellence Award and IBM Outstanding Innovation Award in 2018, IBM Outstanding Technical Achievement Award in 2017, and IBM Research Accomplishment Award in 2009.
Dr. Rish holds 64 patents, has published over 80 research papers, several book chapters, three edited books, and a monograph on Sparse Modeling. She is IEEE TPAMI Associate Editor (since 2019), a member of the AI Journal (AIJ) editorial board (since 2016), served as a Senior Area Chair for NIPS-2017, NIPS-2018, ICML-2018, an Area Chair for ICLR-2019, ICLR-2018, JCAI-2015, ICML-2015, ICML-2016, NIPS-2010, tutorials chair for UAI-2012 and workshop chair for UAI-2015 and ICML-2012; she gave several tutorials (AAAI-1998, AAAI-2000, ICML-2010, ECML-2006) and co-organized multiple workshops at core AI conferences, including 11 workshops at NIPS (from 2003 to 2016), ICML-2008 and ECML-2006.
|Fri 6 March||10h30||Leslie Kaelbling||MIT||Mila Agora||Doing for our robots what nature did for us||We, as robot engineers, have to think hard about our role in the design of robots and how it interacts with learning, both in "the factory" (that is, at engineering time) and in "the wild" (that is, when the robot is delivered to a customer). I will share some general thoughts about the strategies for robot design and then talk in detail about some work I have been involved in, both in the design of an overall architecture for an intelligent robot and in strategies for learning to integrate new skills into the repertoire of an already competent robot.||Leslie Pack Kaelbling is the Panasonic Professor of Computer Science and Engineering at the Computer Science and Artificial Intelligence Laboratory (CSAIL) at the Massachusetts Institute of Technology. She has made research contributions to decision-making under uncertainty, learning, and sensing with applications to robotics, with a particular focus on reinforcement learning and planning in partially observable domains. She holds an A.B in Philosophy and a Ph.D. in Computer Science from Stanford University, and has had research positions at SRI International and Teleos Research and a faculty position at Brown University. She is the recipient of the US National Science Foundation Presidential Faculty Fellowship, the IJCAI Computers and Thought Award, and several teaching prizes; she has been elected a fellow of the AAAI. She was the founder and editor-in-chief of the Journal of Machine Learning Research.|
|Fri 13 March||10h30||Pierre Gentine||Columbia University||Mila Agora||Hybrid modeling: best of both world?||In recent years, we have witnessed an explosion in the applications of machine learning, especially for environmental problems.Yet for broader use, those algorithms may need to respect exactly some physical constraints such as the conservation of mass and energy. In addition, environmental applications (e.g. drought, heat waves) are typically focusing on extremes and on out-of-sample generalization rather than on interpolation. This can be a problem for typical algorithms, which interpolate well but have difficulties extrapolating. I will here show how a hybridization of machine learning algorithms, imposing physical knowledge within them, can help with those different issues and offer a promising avenue for climate applications and process understanding.||Pierre Gentine is an associate professor in Earth and Environmental Engineering at Columbia. He studies the terrestrial water and carbon cycles and their changes with climate change. Pierre Gentine is recipient of the NSF, NASA and DOE early career awards, as well as the American Geophysical Union Global Environmental Changes Early Carrer and American Meteorological Society Meisinger award.|
|Fri 3 April||10h30||TBD||Mila Agora|
|Fri 10 April||10h30||ICLR Lightning Talks|
|Fri 17 April||10h30||Tim O'donnell||Mila||Mila Agora||TBD|
|Fri 24 April||10h30||Ross Otto||McGill||Mila Agora||TBD|