Publications

Mingyu Chen, Aldo Pacchiano, Xuezhou Zhang (2024). State-free Reinforcement Learning.

Aldo Pacchiano (2024). Second Order Bounds for Contextual Bandits with Function Approximation.

Aida Afsar, Aldo Pacchiano (2024). Learning Rate-Free Reinforcement Learning: A Case for Model Selection with Non-Stationary Objectives.

Dipendra Misra*, Aldo Pacchiano*, Robert Schapire* (2024). Provable Interactive Learning with Hindsight Instruction Feedback. ICML 2024.

Yilei Chen, Aldo Pacchiano, Ioannis Ch. Paschalidis (2024). Multiple-policy Evaluation via Density Estimation.

Nirjhar Das, Souradip Chakraborty, Aldo Pacchiano, Sayak Ray Chowdhury (2024). Provably Sample Efficient RLHF via Active Preference Optimization.

Chinmaya Kausik, Mirco Mutti, Aldo Pacchiano, Ambuj Tewari (2024). A Framework for Partially Observed Reward-States in RLHF.

Aldo Pacchiano, Chris Dann, Claudio Gentile (2024). Data-Driven Regret Balancing for Online Model Selection in Bandits. AISTATS 2024.

Aldo Pacchiano, Mohammad Ghavamzadeh, Peter Bartlett (2024). Contextual Bandits with Stage-wise Constraints.

Sinong Geng, Aldo Pacchiano, Andrey Kolobov, Ching-An Cheng (2024). Improving Offline RL by Blending Heuristics. ICLR 2024.

Aldo Pacchiano, Jonathan Lee, Emma Brunskill (2023). Experiment Planning with Function Approximation.

Jonathan Lee, Annie Xie, Aldo Pacchiano, Yash Chandak, Chelsea Finn, Ofir Nachum, Emma Brunskill (2023). Supervised Pretraining Can Learn In-Context Reinforcement Learning.

Parnian Kassraie, Aldo Pacchiano, Nicolas Emmengger, Andreas Krause (2023). Anytime Model Selection in Linear Bandits.

Abhi Gupta, Ted Moskovitz, David Alvarez-Melis, Aldo Pacchiano (2023). Transfer RL via the Undo Maps Formalism.

Nataly Brukhi, Miroslav Dudik, Aldo Pacchiano, Robert Schapire (2023). A Unified Model and Dimension for Interactive Estimation.

Andrew Wagenmaker, Aldo Pacchiano (2023). Leveraging Offline Data in Online Reinforcement Learning. ICML 2023.

Jonathan Lee, Weihao Kong, Aldo Pacchiano, Vidya Muthukumar, Emma Brunskill (2023). Estimating Optimal Policy Value in General Linear Contextual Bandits. TMLR.

Jeffrey Chan*, Aldo Pacchiano*, Nilesh Tripuraneni*, Yun S. Song, Peter Bartlett, Michael Jordan (2023). Parallelizing Contextual Bandits.

Aldo Pacchiano, Drausin Wulsin, Robert A. Barton, Luis Voloch (2023). Neural Design for Genetic Perturbation Experiments. ICLR 2023.

Aldo Pacchiano*, Aadirupa Saha*, Jonathan Lee (2023). Dueling RL: Reinforcement Learning with Trajectory Preferences. AISTATS 2023.

Aldo Pacchiano, Peter Bartlett, Michael Jordan (2022). An Instance-Dependent Analysis for the Cooperative Multi-Player Multi-Armed Bandit. ALT 2023.

Abhishek Gupta*, Aldo Pacchiano*, Yuexiang Zhai, Sham Kakade, Sergey Levine (2022). Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity. NeurIPS 2022.

Jack Parker-Holder*, Yingchen Xu*, Philip Ball*, Aldo Pacchiano*, Oleh Rybkin, Stephen Roberts, Tim Rocktäschel, Edward Grefenstette (2022). Learning General World Models in a Handful of Reward-Free Deployments. NeurIPS 2022.

Aldo Pacchiano, Ofir Nachum, Nilesh Tripuraneni, Peter Bartlett (2022). Joint Representation Training in Sequential Tasks with Shared Structure.

Aldo Pacchiano, Christoph Dann, Claudio Gentile (2022). Best of Both Worlds Model Selection. NeurIPS 2022.

Darren Lin*, Aldo Pacchiano*, Yaodong Yu*, Michael Jordan (2022). Online Nonsubmodular Minimization with Delayed Costs: From Full Information to Bandit Feedback. ICML 2022.

Robert Müller, Aldo Pacchiano (2022). Meta Learning MDPs with Linear Transition Models. AISTATS 2022.

Xingyou Song, Krzysztof Choromanski, Jack Parker-Holder, Yunhao Tang, Qiuyi Zhang, Daiyi Peng, Deepali Jain, Wenbo Gao, Aldo Pacchiano, Tamas Sarlos, Yuxiang Yang (2021). ES-ENAS: Blackbox Optimization over Hybrid Spaces via Combinatorial and Continuous Evolution.

Aldo Pacchiano, Shaun Singh, Edward Chou, Alexander C. Berg, Jakob Foerster (2021). Neural Pseudo-Label Optimism for the Bank Loan Problem. NeurIPS 2021.

Ted Moskovitz, Michael Arbel, Jack Parker-Holder, Aldo Pacchiano (2021). Towards an Understanding of Default Policies in Multitask Policy Optimization. AISTATS 2022.

Matteo Papini, Andrea Trinzioni, Aldo Pacchiano, Marcello Restelli, Alessandro Lazaric, Matteo Pirotta (2021). Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection. NeurIPS 2021.

Krzysztof Choromanski, Deepali Jain, Wenhao Yu, Xingyou Song, Jack Parker-Holder, Tingnan Zhang, Valerii Likhosherstov, Aldo Pacchiano, Anirban Santara, Yunhao Tang, Jie Tan, Adrian Weller (2021). Unlocking Pixels for Reinforcement Learning via Implicit Attention.

Aldo Pacchiano, Philip Ball, Jack Parker-Holder, Krzysztof Choromanski, Stephen Roberts (2021). Towards Tractable Optimism in Model-Based Reinforcement Learning. UAI 2021.

Dhruv Malik, Aldo Pacchiano, Vishwak Srinivasan, Yuanzhi Li (2021). Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity. ICML 2021.

Ashok Cutkosky*, Christoph Dann*, Abhimanyu Das*, Claudio Gentile*, Aldo Pacchiano*, Manish Purohit* (2021). Dynamic Balancing for Model Selection in Bandits and RL. ICML 2021.

Aldo Pacchiano (2021). Model Selection for Contextual Bandits and Reinforcement Learning.

Niladri S. Chatterji*, Aldo Pacchiano*, Peter L. Bartlett, Michael I. Jordan (2021). On the Theory of Reinforcement Learning with Once-per-Episode Feedback. NeurIPS 2021.

Jeffrey Chan*, Aldo Pacchiano*, Nilesh Tripuraneni*, Yun S. Song, Peter Bartlett, Michael Jordan (2021). Parallelizing Contextual Linear Bandits.

Aldo Pacchiano, Mohammad Ghavamzadeh, Peter Bartlett, Heinrich Jiang (2021). Stochastic Bandits with Linear Constraints. AISTATS 2021.

Heinrich Jiang*, Qijia Jiang*, Aldo Pacchiano* (2021). Learning the Truth From Only One Side of the Story. AISTATS 2021.

Aldo Pacchiano, Jonathan Lee, Peter Bartlett, Ofir Nachum (2021). Near Optimal Policy Optimization via REPS. NeurIPS 2021.

Ted Moskovitz, Jack Parker-Holder, Aldo Pacchiano, Michael Arbel, Michael Jordan (2021). Tactical Optimism and Pessimism for Deep Reinforcement Learning. NeurIPS 2021.

Silvia Chiappa*, Aldo Pacchiano* (2021). Fairness with Continuous Optimal Transport.

Jack Parker-Holder, Luke Metz, Cinjon Resnick, Hengyuan Hu, Adam Lerer, Alistair Letcher, Alexander Peysakhovich, Aldo Pacchiano, Jakob Foerster (2020). Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian. NeurIPS 2020.

Aldo Pacchiano*, My Phan*, Yasin Abbasi-Yadkori, Anup Rao, Julian Zimmert, Tor Lattimore, Csaba Szepesvari (2020). Model Selection in Contextual Stochastic Bandit Problems. NeurIPS 2020.

Aldo Pacchiano*, Jack Parker-Holder*, Krzysztof Choromanski, Stephen Roberts (2020). Effective Diversity in Population-Based Reinforcement Learning. NeurIPS 2020.

Krzysztof Choromanski, David Cheikhi, Jared Davis, Valerii Likhosherstov, Achille Nazaret, Achraf Bahamou, Xingyou Song, Mrugank Akarte, Jack Parker-Holder, Jacob Bergquist, Yuan Gao, Aldo Pacchiano, Tamas Sarlos, Adrian Weller, Vikas Sindhwani (2020). Stochastic Flows and Geometric Optimization on the Orthogonal Group. ICML 2020.

Philip Ball, Jack Parker-Holder, Aldo Pacchiano, Krzysztof Choromanski, Stephen Roberts (2020). Ready Policy one: World Building Through Active Learning. ICML 2020.

Eric Mazumdar*, Aldo Pacchiano*, Yian Ma, Michael Jordan, Peter Bartlett (2020). On Approximate Thompson Sampling with Langevin Algorithms. ICML 2020.

Aldo Pacchiano, Jack Parker-Holder, Yunhao Tang, Krzysztof Choromanski, Anna Choromanska, Michael Jordan (2020). Learning to Score Behaviors for Guided Policy Optimization. ICML 2020.

Jonathan Lee, Aldo Pacchiano, Peter Bartlett, Michael Jordan (2020). Accelerated Message Passing for Entropy-Regularized MAP Inference. ICML 2020.

Aldo Pacchiano, Chris Dann, Claudio Gentile, Peter L. Bartlett (2020). Regret Bound Balancing and Elimination for Model Selection in Bandits and RL.

Jonathan Lee, Aldo Pacchiano, Vidya Muthukumar, Weihao Kong, Emma Brunskill (2020). Online Model Selection for Reinforcement Learning with Function Approximation. AISTATS 2021.

Ray Jiang*, Aldo Pacchiano*, Tom Stepleton, Heinrich Jiang, Silvia Chiappa (2020). Wasserstein Fair Classification. UAI 2019.

Robert Müller, Jack Parker-Holder, Aldo Pacchiano (2020). Taming the Herd: Multi-Modal Meta-Learning with a Population of Agents. ICML 2020 Workshop Lifelong ML.

Yasin Abbasi-Yadkori, Aldo Pacchiano, My Phan (2020). Regret Balancing for Bandit and RL Model Selection.

Krzysztof Choromanski*, Aldo Pacchiano*, Jack Parker-Holder*, Yunhao Tang* (2020). Practical Nonisotropic Monte Carlo Sampling in High Dimensions via Determinantal Point Processes. AISTATS 2020.

Jonathan Lee*, Aldo Pacchiano*, Michael Jordan (2020). Convergence Rates of Smooth Message Passing with Rounding in Entropy-Regularized MAP Inference. AISTATS 2020.

Krzysztof Choromanski*, Aldo Pacchiano*, Jack Parker-Holder*, Yunhao Tang, Deepali Jain, Yuxiang Yang, Atil Iscen, Jasmine Hsu, Vikas Sindhwani (2020). Provably Robust Blackbox Optimization for Reinforcement Learning. CoRL 2019.

Aldo Pacchiano, Heinrich Jiang, Michael Jordan (2020). Robustness Guarantees for Mode Estimation with an Application to Bandits. AAAI 2021.

Krzysztof Choromanski*, Aldo Pacchiano*, Jack Parker-Holder*, Yunhao Tang*, Vikas Sindhwani (2019). From Complexity to Simplicity: Adaptive ES-Active Subspaces for Blackbox Optimization. NeurIPS 2019.

Xingyou Song, Wenbo Gao, Yuxiang Yang, Krzysztof Choromanski, Aldo Pacchiano, Yunhao Tang (2019). ES-MAML: Simple Hessian-Free Meta Learning. ICLR 2020.

Xingyou Song, Krzysztof Choromanski, Jack Parker-Holder, Yunhao Tang, Wenbo Gao, Aldo Pacchiano, Tamas Sarlos, Deepali Jain, Yuxiang Yang (2019). Reinforcement Learning with Chromatic Networks for Compact Architecture Search.

Aldo Pacchiano, Yoram Bachrach (2019). Computing Stable Solutions in Threshold Network Flow Games With Bounded Treewidth. AAMAS 2019.

Krzystof Choromanski*, Aldo Pacchiano*, Jeffrey Pennington*, Yunhao Tang* (2019). KAMA-NNs: Low-Dimensional Rotation Based Neural Networks. AISTATS 2019.

Kush Bhatia*, Aldo Pacchiano*, Nicolas Flammarion, Peter Bartlett, Michael Jordan (2018). Gen-Oja: A Two-time-scale approach for Streaming CCA. NeurIPS 2018.

Aldo Pacchiano*, Niladri S. Chatterji*, Peter L. Bartlett (2018). Online learning with kernel losses. In ICML 2019.

Mohammed Amin Abdullah*, Aldo Pacchiano*, Moez Draief (2018). Reinforcement Learning with Wasserstein Distance Regularisation, with Applications to Multipolicy Learning. EWRL 2018.

Mark Rowland, Aldo Pacchiano, Adrian Weller (2017). Conditions Beyond Treewidth for Tightness of Higher-order LP Relaxations. AISTATS 2017.

Aldo Pacchiano, Oliver Williams (2015). Real Time Clustering of Time Series Using Triangular Potentials.

Pavel Etingof, Sherry Gong, Aldo Pacchiano, Qingchun Ren, Travis Schedler (2012). Computational Approaches to Poisson Traces Associated to Finite Subgroups of Sp2n(C). Journal of Experimental Mathematics.

Aldo Pacchiano (0001). Trace Reconstruction Problem.

Mark Rowland, Krzysztof Choromanski, François Chalus, Aldo Pacchiano, Tamas Sarlos, Richard E Turner, Adrian Weller (0001). Geometrically Coupled Monte Carlo Sampling. NeurIPS 2018; spotlight presentation.

Silvia Chiappa, Ray Jiang, Tom Stepleton, Aldo Pacchiano, Heinrich Jiang, John Aslanides (0001). A General Approach to Fairness with Optimal Transport. AAAI 2020.