Search Results for author:
Found 6 papers, 0 papers with code
Bounds on the price of feedback for mistake-bounded online learning
In particular, we sharpen an upper bound for delayed ambiguous reinforcement learning by a factor of 2 and an upper bound for learning compositions of families of functions by a factor of 2. 41.
Online Learning of Smooth Functions
We also obtain sharp bounds on learning $\mathcal F_{\infty, d}$ for $p < d$ when the number of trials is bounded.
Sharp bounds on the price of bandit feedback for several models of mistake-bounded online learning
The only difference between the two models is that in the delayed, ambiguous model, the learner must answer each input before receiving the next input of the round, while the learner receives all $r$ inputs at once in the weak reinforcement model.
Sharper bounds for online learning of smooth functions of a single variable
We investigate the generalization of the mistake-bound model to continuous real-valued single variable functions.
A note on the price of bandit feedback for mistake-bounded online learning
The proof of this result depended on the following lemma, which is false e. g. for all prime $p \ge 5$, $s = \mathbf{1}$ (the all $1$ vector), $t = \mathbf{2}$ (the all $2$ vector), and all $z$.
Stable fixed points of combinatorial threshold-linear networks
We also provide further evidence for the conjecture by showing that sparse graphs and graphs that are nearly cliques can never support stable fixed points.
