Transitions, Losses, and Re-parameterizations: Elements of Prediction Games

05/20/2018
by   Parameswaran Kamalaruban, et al.
0

This thesis presents some geometric insights into three different types of two player prediction games -- namely general learning task, prediction with expert advice, and online convex optimization. These games differ in the nature of the opponent (stochastic, adversarial, or intermediate), the order of the players' move, and the utility function. The insights shed some light on the understanding of the intrinsic barriers of the prediction problems and the design of computationally efficient learning algorithms with strong theoretical guarantees (such as generalizability, statistical consistency, and constant regret etc.).

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

12/31/2021

Stochastic convex optimization for provably efficient apprenticeship learning

We consider large-scale Markov decision processes (MDPs) with an unknown...
02/07/2021

Lazy OCO: Online Convex Optimization on a Switching Budget

We study a variant of online convex optimization where the player is per...
01/14/2020

Smooth markets: A basic mechanism for organizing gradient-based learners

With the success of modern machine learning, it is becoming increasingly...
10/19/2017

Online Monotone Games

Algorithmic game theory (AGT) focuses on the design and analysis of algo...
03/10/2014

Generalised Mixability, Constant Regret, and Bayesian Updating

Mixability of a loss is known to characterise when constant regret bound...
11/18/2019

Learning Probably Approximately Correct Maximin Strategies in Simulation-Based Games with Infinite Strategy Spaces

We tackle the problem of learning equilibria in simulation-based games. ...
04/12/2018

Online convex optimization and no-regret learning: Algorithms, guarantees and applications

Spurred by the enthusiasm surrounding the "Big Data" paradigm, the mathe...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.