conftrace_
← Authors

Paul Mineiro

20 papers · 2013–2024 · 3 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓
+10 more ↓ 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (13) 🌍 Conference Polyglot (3)
πŸ—ΊοΈ Taxonomy Completionist (13) 🧭 Keyword Pioneer πŸ‘‘ Triple Crown 🌱 Topic Pioneer πŸ† Keyword Champion (2) πŸ“ˆ Trend Setter πŸ”₯ Unstoppable (6) πŸš€ Conference Pioneer πŸ—ƒοΈ Keyword Collector (83) πŸ’Ž Century Club (20)

Conferences

ICML (11) NIPS (8) ICLR (1)

Top co-authors

John Langford (7) Nikos Karampatziakis (6) Mengxiao Zhang (3) Haipeng Luo (3) Tengyang Xie (3) Yuheng Zhang (3) Yinglun Zhu (3) Nan Jiang (2) Akanksha Saran (2) Ida Momennejad (2)

Keywords

contextual bandit (6) online learning (4) regret bound (4) policy optimization (3) sample complexity (2) function approximation (2) latent reward (2) multiclass classification (2) continuous action space (2) off-policy evaluation (2) logarithmic time (2) hyperparameter optimization (1) feature extraction (1) uncertainty quantification (1) offline reinforcement learning (1) active learning (1) binary classification (1) empirical risk minimization (1) interactive learning (1) brain-computer interface (1)

Papers

Aligning LLM Agents by Learning Latent Preference from User Edits NIPS 2024 Active, anytime-valid risk controlling prediction sets NIPS 2024 Provably Efficient Interactive-Grounded Learning with Personalized Reward NIPS 2024 Efficient Contextual Bandits with Uninformed Feedback Graphs ICML 2024 Infinite Action Contextual Bandits with Reusable Data Exhaust ICML 2023 Time-uniform confidence bands for the CDF under nonstationarity NIPS 2023 Practical Contextual Bandits with Feedback Graphs NIPS 2023 Personalized Reward Learning with Interaction-Grounded Learning (IGL) ICLR 2023 Contextual Bandits with Smooth Regret: Efficient Learning in Continuous Action Spaces ICML 2022 Contextual Bandits with Large Action Spaces: Made Practical ICML 2022 Interaction-Grounded Learning with Action-Inclusive Feedback NIPS 2022 ChaCha for Online AutoML ICML 2021 Bellman-consistent Pessimism for Offline Reinforcement Learning NIPS 2021 Off-Policy Confidence Sequences ICML 2021 Interaction-Grounded Learning ICML 2021 Empirical Likelihood for Contextual Bandits NIPS 2020 Contextual Memory Trees ICML 2019 Logarithmic Time One-Against-Some ICML 2017 Discriminative Features via Generalized Eigenvectors ICML 2014 Loss-Proportional Subsampling for Subsequent ERM ICML 2013