Minimax-fair machine learning minimizes the error for the worst-off group. However, empirical evidence suggests that when sophisticated models are trained with standard empirical risk minimization (ERM), they often have the same performance on the worst-of ...
We introduce a generic two-loop scheme for smooth minimax optimization with strongly-convex-concave objectives. Our approach applies the accelerated proximal point framework (or Catalyst) to the associated dual problem and takes full advantage of existing ...
We analyze symmetric protocols to rationally coordinate on an asymmetric, efficient allocation in an infinitely repeated N-agent, C-resource allocation problems, where the resources are all homogeneous. Bhaskar proposed one way to achieve this in 2-agent, ...
We analyze resource allocation problems where N independent agents want to access C resources. Each resource can be only accessed by one agent at a time. In order to use the resources efficiently, the agents need to coordinate their access. We focus on dec ...
Model compression techniques have lead to a reduction of size and number of computations of Deep Learning models. However, techniques such as pruning mostly lack of a real co-optimization with hardware platforms. For instance, implementing unstructured pru ...
We examine the problem of regret minimization when the learner is involved in a continuous game with other optimizing agents: in this case, if all players follow a no-regret algorithm, it is possible to achieve significantly lower regret relative to fully ...
It is natural for humans to judge the outcome of a decision under uncertainty as a percentage of an ex-post optimal performance. We propose a robust decision-making framework based on a relative performance index. It is shown that if the decision maker’s p ...
We consider a participatory sensing scenario where a group of private sensors observes the same phenomenon, such as air pollution. Since sensors need to be installed and maintained, owners of sensors are inclined to provide inaccurate or random data. We de ...
We investigate the problem of multi-agent coordination under rationality constraints. Specifically, role allocation, task assignment, resource allocation, etc. Inspired by human behavior, we propose a framework (CA^3NONY) that enables fast convergence to e ...
International Foundation for Autonomous Agents and Multiagent Systems2019
We consider a participatory sensing scenario where a group of private sensors observes the same phenomenon, such as air pollution. We design a novel payment mechanism that incentivizes participation and honest behavior using the peer prediction approach, i ...
