# Selected Talks

The talks listed here are higher-level survey-type talks. For talks about specific research results, please see my publications page.- From Machine Learning to Optimization August 2023. Intended Audience: Computer scientists, sports analytics, statisticians. Given at the Opt4Sports workshop at CP2023. A high-level survey of how machine learning can be applied in sports analytics and optimization problems that can make the results of machine learning actionable for practioners.
- Machine Learning for Information Networks February 2018. Intended Audience: Computer scientists. Given at the University of Toronto. A brief summary of my work on learning graphical models for multi-relational data. It was fun to be back at the U of T, brought back many memories from my undergraduate days.
- What is the value of an action in ice hockey? March 2019. Intended Audience: Computer scientists, operations researchers. Given at CAIDA UBC. An introduction to player evaluation in ice hockey, presenting our latest approach based on approximating a value function for the NHL using a neural net and deep reinforcement learning.
- From Learning Theory to Particle Physics. October 2015. Intended Audience: Philosophers and Logicians. Given at Carnegie Mellon University. A brief summary of my theoretical work on reliable and efficient learning, with a number of applications. This talk was part of the 30-year celebration of the founding of the philosophy department at CMU. I was honoured to be invited to present. It was the first time I participated in celebrating 30 years of anything actually.
- From Relational Statistics to Degrees of Belief: Learning Bayesian Networks for Relational Databases.
November 2015
PDF Version.

Intended Audience: Computer Scientists. Given at KU Leuven and University of Bristol. An overview of issues, concepts, and applications of logic, probability, and Bayesian Network learning for Relational Databases. Explains briefly parameter learning and structure learning algorithms. - From Relational Statistics to Degrees of Belief: Learning Bayesian Networks for Relational Databases.
November 2015
PDF Version.

Intended Audience: Computer Scientists. Given at KU Leuven and University of Bristol. An overview of issues, concepts, and applications of logic, probability, and Bayesian Network learning for Relational Databases. Explains briefly parameter learning and structure learning algorithms. - A Hierarchy of Independence Assumptions for Multi-Relational Bayes Net Classifiers.
April 2013.
PDF Version.

Intended Audience: Computer Scientists. Given at IEEE Symposium Series on Computational Intelligence. Constructs a hierarchy of different independence assumptions multi-relational classification, from weaker to stronger assumptions. For instance, we may assume that links are conditionally independent, or that the class label is independent of the existence of links. We mathematically derive multi-relational classification formulas for each level in the hierarchy; all these formulas are log-linear models. Some of these formulas have been proposed before, so our hierarchy unifies previously disparate ideas in the field. The weakest assumption at the top of the hierarchy seems to provide a sweet spot: strong enough to decompose multi-relational classification for fast learning, weak enough to allow accurate prediction. -
**A Pseudo-Likelihood Function for Relational Data.**A fundamental difficulty in learning Bayes Nets for relational or network data is to define a likelihood function that measures how well a statistical model fits a database. The reason this is difficult is that the usual product likelihood function assumes that population units are independent, whereas in relational data, by definition units, are interdependent. My proposed solution is to consider the expected likelihood of a model for small, randomly selected subgroups of units. Here are two talks presenting this idea, for different audiences.- Intended Audience: Statisticians.
A big picture talk, with fairly extensive explanations of logic and
relational databases as well as Bayes nets and probability theory.
April 2011. PDF Version.

- Intended Audience: Computer Scientists. A short conference talk, presenting the basic idea.
February 2011. PDF Version.

- Intended Audience: Statisticians.
A big picture talk, with fairly extensive explanations of logic and
relational databases as well as Bayes nets and probability theory.
April 2011. PDF Version.
- Discovery of Conservation Laws.
Oct 2010. PDF Version.

Intended Audience: Computer Scientists. Given at Discovery Science 2010 conference. Presents a new criterion for selecting conservation laws: they should be maximally simple and maximally strict. Formally, minimize the L1-norm subject to the constraint that they rule out as many unobserved reaction as possible. We provide an efficient optimization algorithm for this new criterion. The procedure rediscovers conservation principles in molecular chemistry and in the fundamental Standard Model of Particle Physics. - Causal Modelling for Relational Data.
July 2010. PDF Version.

Intended Audience: Logicians, Computer Scientists, Epistemologists. Given at CMU. An outline of what I see as the main difficulties in statistical-relational learning. Presents briefly our new learn-and-join algorithm for Bayes net structure learning with relational data. Also a new semantics for relational Bayes nets, based on random groundings rather than a ground model. - The IMAP Hybrid Method for Learning Gaussian Bayes Nets.
May 2010. PDF Version.

Intended Audience: Computer Scientists, Statisticians. A conference talk on hybrid methods for learning Bayes nets. Presents constraint-based methods, score-based methods, and a new way to combine them. This paper won the best paper award - thank you CanAI! - Three Applications of Means-Ends Epistemology.
February 2008.

Intended Audience: Philosophers and Computer Scientists (given at Caltech Philosophy Seminar). Presents three applications of formal learning theory as a package: Discovering conservation laws in particle physics, solving Goodman's Riddle of Induction and learning causal models from observed correlations. - Mind Change Optimal Learning of Bayes Net Structure.
June 2007.

Intended Audience: Computer Scientists. Presents our results on the mind change complexity of learning Bayes nets from correlation data. Contains a simple example of the mind change optimal learning method (minimizing the number of edges), and a brief outline of the NP-hardness proof for this method. - Evolutionary Equilibria in Network Routing Games: Specialization and Clustering. Nov 2005.

Intended Audience: Computer Scientists. Joint work with Petra Berenbrink. Presents a model of network traffic where users choose the routes for their messages by themselves. We analyze the evolutionary equilibria of such games, and find that evolution leads to the formation of "niches" in which links "specialize" in certain tasks. These network games are closely related to congestion games. - The Evidence for Conservation Laws and Particle Families. May 2005.

Intended Audience: Philosophers of Physics, Physicists. Similar to previous talk, but with more technical details. Also a brief overview of the methods for inferring the existence of unobserved particles and the application to the question of whether the electron neutrino is a Majorana particle. University of Western Ontario. - How Particle Physics Cuts Nature At Its Joints. May 2005.

Intended Audience: Philosophers of Science. Discusses the results of my algorithms and analysis of finding conservation laws corresponding to particle families. With reference to traditional philosophical issues such as skepticism, underdetermination, nominalism, natural kinds, laws of nature. University of Washington. - Learning Conservation Principles in Particle Physics. March 2005.

Intended Audience: Computer Scientists. A brief overview of my algorithms for finding conserved quantities and hidden particles in particle reactions. Laboratory for Computational Intelligence, University of British Columbia. - Automated Search for Conserved Quantities in Particle Reactions. February 2005.

Intended Audience: Physicists. An overview of most of my results on algorithms for finding conserved quantities and hidden particles in particle reactions - see NSERC project. Particle Physics Group, Simon Fraser University.