Alert button
Picture for Paul Mineiro

Paul Mineiro

Alert button

Efficient Contextual Bandits with Uninformed Feedback Graphs

Feb 12, 2024
Mengxiao Zhang, Yuheng Zhang, Haipeng Luo, Paul Mineiro

Viaarxiv icon

Time-uniform confidence bands for the CDF under nonstationarity

Feb 28, 2023
Paul Mineiro, Steven R. Howard

Figure 1 for Time-uniform confidence bands for the CDF under nonstationarity
Figure 2 for Time-uniform confidence bands for the CDF under nonstationarity
Figure 3 for Time-uniform confidence bands for the CDF under nonstationarity
Figure 4 for Time-uniform confidence bands for the CDF under nonstationarity
Viaarxiv icon

Graph Feedback via Reduction to Regression

Feb 17, 2023
Paul Mineiro

Figure 1 for Graph Feedback via Reduction to Regression
Figure 2 for Graph Feedback via Reduction to Regression
Figure 3 for Graph Feedback via Reduction to Regression
Viaarxiv icon

Infinite Action Contextual Bandits with Reusable Data Exhaust

Feb 16, 2023
Mark Rucker, Yinglun Zhu, Paul Mineiro

Figure 1 for Infinite Action Contextual Bandits with Reusable Data Exhaust
Figure 2 for Infinite Action Contextual Bandits with Reusable Data Exhaust
Figure 3 for Infinite Action Contextual Bandits with Reusable Data Exhaust
Viaarxiv icon

Personalized Reward Learning with Interaction-Grounded Learning (IGL)

Nov 28, 2022
Jessica Maghakian, Paul Mineiro, Kishan Panaganti, Mark Rucker, Akanksha Saran, Cheng Tan

Figure 1 for Personalized Reward Learning with Interaction-Grounded Learning (IGL)
Figure 2 for Personalized Reward Learning with Interaction-Grounded Learning (IGL)
Figure 3 for Personalized Reward Learning with Interaction-Grounded Learning (IGL)
Figure 4 for Personalized Reward Learning with Interaction-Grounded Learning (IGL)
Viaarxiv icon

Towards Data-Driven Offline Simulations for Online Reinforcement Learning

Nov 14, 2022
Shengpu Tang, Felipe Vieira Frujeri, Dipendra Misra, Alex Lamb, John Langford, Paul Mineiro, Sebastian Kochman

Figure 1 for Towards Data-Driven Offline Simulations for Online Reinforcement Learning
Figure 2 for Towards Data-Driven Offline Simulations for Online Reinforcement Learning
Figure 3 for Towards Data-Driven Offline Simulations for Online Reinforcement Learning
Figure 4 for Towards Data-Driven Offline Simulations for Online Reinforcement Learning
Viaarxiv icon

Eigen Memory Trees

Oct 31, 2022
Mark Rucker, Jordan T. Ash, John Langford, Paul Mineiro, Ida Momennejad

Figure 1 for Eigen Memory Trees
Figure 2 for Eigen Memory Trees
Figure 3 for Eigen Memory Trees
Figure 4 for Eigen Memory Trees
Viaarxiv icon

Deploying a Steered Query Optimizer in Production at Microsoft

Oct 24, 2022
Wangda Zhang, Matteo Interlandi, Paul Mineiro, Shi Qiao, Nasim Ghazanfari Karlen Lie, Marc Friedman, Rafah Hosn, Hiren Patel, Alekh Jindal

Figure 1 for Deploying a Steered Query Optimizer in Production at Microsoft
Figure 2 for Deploying a Steered Query Optimizer in Production at Microsoft
Figure 3 for Deploying a Steered Query Optimizer in Production at Microsoft
Figure 4 for Deploying a Steered Query Optimizer in Production at Microsoft
Viaarxiv icon

Conditionally Risk-Averse Contextual Bandits

Oct 24, 2022
Mónika Farsang, Paul Mineiro, Wangda Zhang

Figure 1 for Conditionally Risk-Averse Contextual Bandits
Figure 2 for Conditionally Risk-Averse Contextual Bandits
Figure 3 for Conditionally Risk-Averse Contextual Bandits
Figure 4 for Conditionally Risk-Averse Contextual Bandits
Viaarxiv icon

Anytime-valid off-policy inference for contextual bandits

Oct 19, 2022
Ian Waudby-Smith, Lili Wu, Aaditya Ramdas, Nikos Karampatziakis, Paul Mineiro

Figure 1 for Anytime-valid off-policy inference for contextual bandits
Figure 2 for Anytime-valid off-policy inference for contextual bandits
Figure 3 for Anytime-valid off-policy inference for contextual bandits
Figure 4 for Anytime-valid off-policy inference for contextual bandits
Viaarxiv icon