Safe Probability
We formalize the idea of probability distributions that lead to reliable predictions about some, but not all aspects of a domain. The resulting notion of `safety' provides a fresh perspective on foundational issues in statistics, providing a middle ground between imprecise probability and multiple-prior models on the one hand and strictly Bayesian approaches on the other. It also allows us to formalize fiducial distributions in terms of the set of random variables that they can safely predict, thus taking some of the sting out of the fiducial idea. By restricting probabilistic inference to safe uses, one also automatically avoids paradoxes such as the Monty Hall problem. Safety comes in a variety of degrees, such as "validity" (the strongest notion), "calibration", "confidence safety" and "unbiasedness" (almost the weakest notion).
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Finding Safe Zones of policies Markov Decision Processes
Given a policy of a Markov Decision Process, we define a SafeZone as a subset of states, such that most of the policy's trajectories are confined to this subset. The quality of a SafeZone is parameterized by the number o…
Connecting Surrogate Safety Measures to Crash Probablity via Causal Probabilistic Time Series Prediction
Surrogate safety measures can provide fast and pro-active safety analysis and give insights on the pre-crash process and crash failure mechanism by studying near misses. However, validating surrogate safety measures by c…
counterfactualOpen-Ended Question AnsweringTime SeriesTime Series Analysis+1Finding Safe Zones of Markov Decision Processes Policies
Given a policy of a Markov Decision Process, we define a SafeZone as a subset of states, such that most of the policy's trajectories are confined to this subset. The quality of a SafeZone is parameterized by the number o…
Virtuously Safe Reinforcement Learning
We show that when a third party, the adversary, steps into the two-party setting (agent and operator) of safely interruptible reinforcement learning, a trade-off has to be made between the probability of following the op…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Safe Exploration+1GoSafe: Globally Optimal Safe Robot Learning
When learning policies for robotic systems from data, safety is a major concern, as violation of safety constraints may cause hardware damage. SafeOpt is an efficient Bayesian optimization (BO) algorithm that can learn p…
Bayesian Optimization