ﻻ يوجد ملخص باللغة العربية
Given a mixture between two populations of coins, positive coins that each have -- unknown and potentially different -- bias $geqfrac{1}{2}+Delta$ and negative coins with bias $leqfrac{1}{2}-Delta$, we consider the task of estimating the fraction $rho$ of positive coins to within additive error $epsilon$. We achieve an upper and lower bound of $Theta(frac{rho}{epsilon^2Delta^2}logfrac{1}{delta})$ samples for a $1-delta$ probability of success, where crucially, our lower bound applies to all fully-adaptive algorithms. Thus, our sample complexity bounds have tight dependence for every relevant problem parameter. A crucial component of our lower bound proof is a decomposition lemma (see Lemmas 17 and 18) showing how to assemble partially-adaptive bounds into a fully-adaptive bound, which may be of independent interest: though we invoke it for the special case of Bernoulli random variables (coins), it applies to general distributions. We present simulation results to demonstrate the practical efficacy of our approach for realistic problem parameters for crowdsourcing applications, focusing on the rare events regime where $rho$ is small. The fine-grained adaptive flavor of both our algorithm and lower bound contrasts with much previous work in distributional testing and learning.
We develop new adaptive algorithms for variational inequalities with monotone operators, which capture many problems of interest, notably convex optimization and convex-concave saddle point problems. Our algorithms automatically adapt to unknown prob
Uncertainty quantification in neural networks gained a lot of attention in the past years. The most popular approaches, Bayesian neural networks (BNNs), Monte Carlo dropout, and deep ensembles have one thing in common: they are all based on some kind
Reinforcement learning agents are faced with two types of uncertainty. Epistemic uncertainty stems from limited data and is useful for exploration, whereas aleatoric uncertainty arises from stochastic environments and must be accounted for in risk-se
We study the combinatorial pure exploration problem Best-Set in stochastic multi-armed bandits. In a Best-Set instance, we are given $n$ arms with unknown reward distributions, as well as a family $mathcal{F}$ of feasible subsets over the arms. Our g
The cooperative control applied to vehicles allows the optimization of traffic on the roads. There are many aspects to consider in the case of the operation of autonomous vehicles on highways since there are different external parameters that can be