We develop the concept of exponential stochastic inequality (ESI), a nov...
Sequential decision making significantly speeds up research and is more
...
The no-free-lunch theorems promote a skeptical conclusion that all possi...
Studies accumulate over time and meta-analyses are mainly retrospective....
We present a new PAC-Bayesian generalization bound. Standard bounds cont...
We present a novel notion of complexity that interpolates between and
ge...
We present new excess risk bounds for general unbounded loss functions
i...
The speed with which a learning algorithm converges as it is presented w...
We consider how an agent should update her uncertainty when it is repres...
It is commonly-accepted wisdom that more information is better, and that...
As examples such as the Monty Hall puzzle show, applying conditioning to...
We consider how an agent should update her beliefs when her beliefs are
...
We analyze differences between two information-theoretically motivated
a...
We give an interpretation of the Maximum Entropy (MaxEnt) Principle in
g...
Follow-the-Leader (FTL) is an intuitive sequential prediction strategy t...