Events

Svetlana Obraztsova
Nanyang Technological University

Traditionally, computational social choice focuses on evaluating voting rules by their resistance to strategic behaviours, and uses computational complexity as a barrier to them. In contrast, recent works (counting from 2010) take another natural approach and analyse voting scenarios from a game-theoretic perspective, viewing strategic parties as players and examining possible stable outcomes of their interaction (i.e., equilibria). The main problem of this approach is multiple unrealistic Nash equilibria. Fortunately, several refinements have been developed that allow to filter out some undesirable Nash Equilibria. 

Yingluo Xun, Master’s candidate
David R. Cheriton School of Computer Science

In reinforcement learning, entropy-regularized value function (in policy space) has attracted a lot of attention recently due to its effect on smoothing the value function, and the effect on encouraging exploration. However, there is a discrepancy between the regularized objective function and the original objective function in existing methods, which would potentially result in a discrepancy between the trained policy and the optimal policy, as the policy directly depends on the value function in the reinforcement learning framework. 

Shrinu Kushagra, PhD candidate
David R. Cheriton School of Computer Science

Clustering aims to group together data instances which are similar while simultaneously separating the dissimilar instances. The task of clustering is challenging due to many factors. The most well-studied is the high computational cost. The clustering task can be viewed as an optimization problem where the goal is to minimize a certain cost function (like k-means cost or k-median cost). Not only are the minimization problems NP-Hard but often also NP-Hard to approximate (within a constant factor). There are two other major issues in clustering, namely under-specificity and noise-robustness. 

Priyank Jaini, PhD candidate
David R. Cheriton School of Computer Science

Triangular map is a recent construct in probability theory that allows one to transform any source probability density function to any target density function. Based on triangular maps, we propose a general framework for high-dimensional density estimation, by specifying one-dimensional transformations (equivalently conditional densities) and appropriate conditioner networks.

Greg d’Eon, Master’s candidate
David R. Cheriton School of Computer Science

Collaborative crowdsourcing tasks allow workers to solve more difficult problems than they could alone, but motivating workers in these tasks is complex. In this thesis, we study how to use payments to motivate groups of crowd workers. We leverage concepts from equity theory and cooperative game theory to understand the connection between fair payments and motivation.