Thorsten Joachims

30 papers · 2005–2025 · 10 conferences · across top CS/AI conferences

Achievements

+11 more ↓

🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🌈 Renaissance Researcher (6) 🗺️ Taxonomy Completionist (17) 🐣 Hot Topic Early Bird

🏃 Academic Marathon (20) 🧭 Keyword Pioneer 🌍 Conference Polyglot (10) 🌟 Keyword Trendsetter Combo (5) 🌱 Topic Pioneer 🏆 Keyword Champion 💎 Century Club (30) 📈 Trend Setter 🚀 Conference Pioneer 🔥 Unstoppable (8) 🗃️ Keyword Collector (50)

Conferences

ICML (10) NIPS (7) AISTATS (2) EMNLP (2) ICLR (2) IJCAI (2) JMLR (2) EACL (1) ICCV (1) UAI (1)

Top co-authors

Adith Swaminathan (6) Tobias Schnabel (4) Ashudeep Singh (4) Yuta Saito (3) Lequn Wang (3) Ashutosh Saxena (2) Pannaga Shivaswamy (2) Wen Sun (2) Kianté Brantley (2) Zohar Karnin (1)

Keywords

contextual bandit (5) regret bound (4) multi-armed bandit (4) counterfactual risk minimization (3) bandit feedback (3) propensity scoring (2) off-policy evaluation (2) group fairness (2) policy evaluation (2) policy optimization (2) implicit feedback (2) off-policy learning (2) recommendation system (2) counterfactual learning (2) importance sampling (2) policy learning (2) online learning (2) importance weighting (2) learning to rank (2) inverse propensity score (2)

Papers

POTEC: Off-Policy Contextual Bandits for Large Action Spaces via Policy Decomposition ICLR 2025 REBEL: Reinforcement Learning via Regressing Relative Rewards NIPS 2024 Coactive Learning for Large Language Models using Implicit User Feedback ICML 2024 Off-Policy Evaluation for Large Action Spaces via Conjunct Effect Modeling ICML 2023 Boosted Off-Policy Learning AISTATS 2023 Bandits with costly reward observations UAI 2023 Improving Screening Processes via Calibrated Subset Selection ICML 2022 Off-Policy Evaluation for Large Action Spaces via Embeddings ICML 2022 Fairness in Ranking under Uncertainty NIPS 2021 Controlling Fairness and Bias in Dynamic Learning-to-Rank (Extended Abstract) IJCAI 2021 Fairness of Exposure in Stochastic Bandits ICML 2021 MOReL: Model-Based Offline Reinforcement Learning NIPS 2020 CAB: Continuous Adaptive Blending for Policy Evaluation and Learning ICML 2019 Policy Learning for Fairness in Ranking NIPS 2019 Deep Learning with Logged Bandit Feedback ICLR 2018 Unbiased Learning-to-Rank with Biased Feedback IJCAI 2018 Recommendations as Treatments: Debiasing Learning and Evaluation ICML 2016 Evaluation methods for unsupervised word embeddings EMNLP 2015 The Self-Normalized Estimator for Counterfactual Learning NIPS 2015 Counterfactual Risk Minimization: Learning from Logged Bandit Feedback ICML 2015 Batch Learning from Logged Bandit Feedback through Counterfactual Risk Minimization JMLR 2015 Invited Talk: Learning from Rational Behavior EMNLP 2014 Reducing Dueling Bandits to Cardinal Bandits ICML 2014 Stable Coactive Learning via Perturbation ICML 2013 Learning Trajectory Preferences for Manipulators via Iterative Improvement NIPS 2013 Structured Learning of Sum-of-Submodular Higher Order Energy Functions ICCV 2013 Large-Margin Learning of Submodular Summarization Models EACL 2012 Multi-armed Bandit Problems with History AISTATS 2012 Semantic Labeling of 3D Point Clouds for Indoor Scenes NIPS 2011 Large Margin Methods for Structured and Interdependent Output Variables JMLR 2005