Results 91 to 100 of about 492,986 (210)
Conservative Contextual Linear Bandits
CoRR, 2016 Safety is a desirable property that can immensely increase the applicability of learning algorithms in real-world decision-making problems. It is much easier for a company to deploy an algorithm that is safe, i.e., guaranteed to perform at least as well as a baseline.
Abbas Kazerouni +3 more
openaire +3 more sources
Context Attentive Bandits: Contextual Bandit with Restricted Context [PDF]
Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, 2017 We consider a novel formulation of the multi-armed bandit model, which we call the contextual bandit with restricted context, where only a limited number of features can be accessed by the learner at every iteration. This novel formulation is motivated by different online problems arising in clinical trials, recommender systems and attention modeling ...
Djallel Bouneffouf 0001 +3 more
openaire +4 more sources
Permission to Dream: The Marxist Ban on Imagining Utopia Reconsidered
Constellations, EarlyView.
Paula Keller
wiley +1 more source
The Enemy Who Never Went Away: Memory, Nationalism and China's Japan Policy During the Cold War
Nations and Nationalism, EarlyView.ABSTRACT This study reassesses the relationship between war memory, nationalism and Sino–Japanese relations during the Cold War. Contrary to the dominant view in existing scholarship that China's nationalist remembering of the war emerged during the 1980s and 1990s, this article, drawing on an extensive survey of the People's Daily, demonstrates that ...
Yi Wang
wiley +1 more source
Conformal Off-Policy Prediction in Contextual Bandits
, 2022 Most off-policy evaluation methods for contextual bandits have focused on the expected outcome of a policy, which is estimated via methods that at best provide only asymptotic guarantees. However, in many applications, the expectation may not be the best
Taufiq, Muhammad Faaiz +4 more
core
Nonparametric Stochastic Contextual Bandits
Proceedings of the AAAI Conference on Artificial Intelligence, 2018 We analyze the K-armed bandit problem where the reward for each arm is a noisy realization based on an observed context under mild nonparametric assumptions.We attain tight results for top-arm identification and a sublinear regret of Õ(T1+D/(2+D), where D is the context dimension, for a modified UCB algorithm that is simple to implement.
Melody Y. Guan, Heinrich Jiang
openaire +4 more sources
Noûs, EarlyView.ABSTRACT I argue that knowledge plays a distinctive role in psychological explanation that weaker epistemic states cannot because it is robust in the face of counterevidence in a way that they are not. Being robust in the face of counterevidence makes your belief robust in the face of counterargument.
Spencer Paulson
wiley +1 more source
Efficient and Robust High-Dimensional Linear Contextual Bandits
, 2020 The linear contextual bandits is a sequential decision-making problem where an agent decides among sequential actions given their corresponding contexts.
Luo Luo +9 more
core +1 more source
Algorithmic Monoculture and Its Critics
Philosophical Perspectives, EarlyView.ABSTRACT Algorithmic decision‐making is replacing idiosyncratic human judgment in domains such as hiring, lending, and criminal justice. This shift promises increased consistency, but many scholars worry that it can go too far. They warn of the dangers of algorithmic monoculture, in which all decisions across a domain are made using a single algorithm.
Brian Hedden, Manish Raghavan
wiley +1 more source
Contextual Bandits with Random Projection
CoRR, 2019 Contextual bandits with linear payoffs, which are also known as linear bandits, provide a powerful alternative for solving practical problems of sequential decisions, e.g., online advertisements. In the era of big data, contextual data usually tend to be high-dimensional, which leads to new challenges for traditional linear bandits mostly designed for ...
openaire +3 more sources