Publications

Ben London, Alexander Buchholz, Giuseppe Di Benedetto, Jan Malte Lichtenberg, Yannik Stein, Thorsten Joachims (2023). Self-Normalized Off-Policy Estimators for Ranking. CONSEQUENCES Workshop – RecSys.

Olivier Jeunen, Ben London (2023). Offline Recommender System Evaluation under Unobserved Confounding. CONSEQUENCES Workshop – RecSys.

Jan Malte Lichtenberg, Alexander Buchholz, Giuseppe Di Benedetto, Matteo Ruffini, Ben London (2023). Double clipping: Less-biased variance reduction in off-policy evaluation. CONSEQUENCES Workshop – RecSys.

Giuseppe Di Benedetto, Alexander Buchholz, Ben London, Matej Jakimov, Yannik Stein, Jan Malte Lichtenberg, Vito Bellini, Matteo Ruffini (2023). Contextual Position Bias Estimation Using a Single Stochastic Logging Policy. LERI Workshop – RecSys.

Ben London, Levi Lu, Ted Sandler, Thorsten Joachims (2023). Boosted Off-Policy Learning. International Conference on Artificial Intelligence and Statistics.

Alexander Buchholz, Ben London, Giuseppe Benedetto, Thorsten Joachims (2022). Off-Policy Evaluation for Learning-to-Rank via Interpolating the Item-Position Model and the Position-Based Model. CONSEQUENCES+REVEAL Workshop – RecSys.

Ben London, Thorsten Joachims (2022). Control Variate Diagnostics for Detecting Problems in Logged Bandit Feedback. CONSEQUENCES+REVEAL Workshop – RecSys.

Thorsten Joachims, Ben London, Yi Su, Adith Swaminathan, Lequn Wang (2021). Recommendations as Treatments. A.I. Magazine.

Ben London (2020). PAC-Identifiability in Federated Learning. NIPS Workshop on Scalability, Privacy and Security in Federated Learning.

Ben London, Thorsten Joachims (2020). Offline Policy Evaluation with New Arms. NIPS Workshop on Offline Reinforcement Learning.

Ofer Meshi, Ben London, David Weller, David Sontag (2019). Train and Test Tightness of LP Relaxations in Structured Prediction. Journal of Machine Learning Research.

Ben London, Ted Sandler (2019). Bayesian Counterfactual Risk Minimization. International Conference on Machine Learning (ICML).

Sabina Tomkins, Steve Isley, Ben London, Lise Getoor (2018). Sustainability at Scale: Bridging the Intention-Behavior Gap with Sustainable Recommendations. Recommender Systems (RecSys).

Ben London, Ted Sandler (2018). Bayesian Counterfactual Risk Minimization. ICML Workshop on Machine Learning for Causal Inference, Counterfactual Prediction, and Autonomous Action (CausalML).

Ben London (2017). A PAC-Bayesian Analysis of Randomized Learning with Application to Stochastic Gradient Descent. Neural Information Processing Systems.

Ben London, Bert Huang, Lise Getoor (2016). Stability and Generalization in Structured Prediction. Journal of Machine Learning Research.

Ben London, Alexander Schwing (2016). Generative Adversarial Structured Networks. NIPS Workshop on Adversarial Training.

Ben London (2016). Generalization Bounds for Randomized Learning with Application to Stochastic Gradient Descent. NIPS Workshop on Optimizing the Optimizers.

Ben London, Ofer Meshi, David Weller (2016). Bounding the Integrality Distance of LP Relaxations for Structured Prediction. NIPS Workshop on Optimization for ML.

Ben London, Bert Huang, Lise Getoor (2015). The Benefits of Learning with Strongly Convex Approximate Inference. International Conference on Machine Learning (ICML).

Jay Pujara, Ben London, Lise Getoor, William Cohen (2015). Online Inference for Knowledge Graph Construction.. Workshop on Statistical Relational AI.

Ben London (2015). On the Stability of Structured Prediction.

Galileo Mark Namata, Ben London, Lise Getoor (2015). Collective Graph Identification. ACM Transactions on Knowledge Discovery from Data.

Jay Pujara, Ben London, Lise Getoor (2015). Budgeted Online Collective Inference. Uncertainty in Artificial Intelligence.

Ben London, Bert Huang, Benjamin Taskar, Lise Getoor (2014). PAC-Bayesian Collective Stability. International Conference on Artificial Intelligence and Statistics.

Ben London, Bert Huang, Lise Getoor (2014). On the Strong Convexity of Variational Inference. NIPS Workshop on Advances in Variational Inference.

Ben London, Bert Huang, Benjamin Taskar, Lise Getoor (2013). PAC-Bayes Generalization Bounds for Randomized Structured Prediction. NIPS Workshop on Perturbation, Optimization and Statistics.

Ben London, Theodoros Rekatsinas, Bert Huang, Lise Getoor (2013). Multi-relational Learning Using Weighted Tensor Decomposition with Modular Loss.

Stephen H. Bach, Bert Huang, Ben London, Lise Getoor (2013). Hinge-loss Markov Random Fields: Convex Inference for Structured Prediction. Uncertainty in Artificial Intelligence.

Ben London, Bert Huang, Lise Getoor (2013). Graph-based Generalization Bounds for Learning Binary Relations.

Bert Huang, Ben London, Benjamin Taskar, Lise Getoor (2013). Empirical Analysis of Collective Stability. ICML Workshop on Structured Learning (SLG).

Ben London, Bert Huang, Benjamin Taskar, Lise Getoor (2013). Collective Stability in Structured Prediction: Generalization from One Example. International Conference on Machine Learning (ICML).

Ben London, Lise Getoor (2013). Collective Classification of Network Data. Data Classification: Algorithms and Applications.

Ben London, Sameh Khamis, Stephen H. Bach, Bert Huang, Lise Getoor, Larry Davis (2013). Collective Activity Detection using Hinge-loss Markov Random Fields. CVPR Workshop on Structured Prediction: Tractability, Learning and Inference.

Galileo Mark Namata, Ben London, Lise Getoor, Bert Huang (2012). Query-driven Active Surveying for Collective Classification. Workshop on Mining and Learning with Graphs.

Ben London, Theodoros Rekatsinas, Bert Huang, Lise Getoor (2012). Multi-relational Weighted Tensor Decomposition. NIPS Workshop on Spectral Learning.

Ben London, Bert Huang, Lise Getoor (2012). Improved Generalization Bounds for Large-scale Structured Prediction. NIPS Workshop on Algorithmic and Statistical Approaches for Large Social Networks.

Jay Pujara, Ben London, Lise Getoor (2011). Reducing Label Cost by Combining Feature Labels and Crowdsourcing. ICML Workshop on Combining Learning Strategies to Reduce Label Cost.