Beginning with Witkowski et al. [2022], recent work on forecasting
compe...
Constant-function market makers (CFMMs), such as Uniswap, are automated
...
We initiate the study of proper losses for evaluating generative models ...
Top-k classification is a generalization of multiclass classification us...
The Lovász hinge is a convex surrogate recently proposed for structured
...
In the classic scoring rule setting, a principal incentivizes an agent t...
Games are natural models for multi-agent machine learning settings, such...
Sofic shifts are symbolic dynamical systems defined by the set of bi-inf...
Inspired by Aumann's agreement theorem, Scott Aaronson studied the amoun...
Surrogate risk minimization is an ubiquitous paradigm in supervised mach...
Kakade, Kearns, and Ortiz (KKO) introduce a graph-theoretic generalizati...
A growing number of machine learning architectures, such as Generative
A...
Winner-take-all competitions in forecasting and machine-learning suffer ...
Given a prediction task, understanding when one can and cannot design a
...
We consider several computational problems related to conjugacy between
...
We formalize and study the natural approach of designing convex surrogat...
Recent work shows that we can use partial verification instead of money ...
A property is a real- or vector-valued function on a set of probability
...
A property is a real- or vector-valued function on a set of probability
...
Recent work introduced loss functions which measure the error of a predi...
Prediction markets are well-studied in the case where predictions are
pr...
We study information elicitation in cost-function-based combinatorial
pr...