Filter by Keyword:

126 Results

Spotlight
Tue 5:20 Offline Contextual Bandits with Overparameterized Models
David Brandfonbrener, Will Whitney, Rajesh Ranganath, Joan Bruna
Spotlight
Tue 5:30 Bias-Robust Bayesian Optimization via Dueling Bandits
Johannes Kirschner, Andreas Krause
Poster
Tue 9:00 Offline Contextual Bandits with Overparameterized Models
David Brandfonbrener, Will Whitney, Rajesh Ranganath, Joan Bruna
Poster
Tue 9:00 Bias-Robust Bayesian Optimization via Dueling Bandits
Johannes Kirschner, Andreas Krause
Spotlight
Tue 17:25 Adapting to Delays and Data in Adversarial Multi-Armed Bandits
András György, Pooria Joulani
Spotlight
Tue 18:40 Probabilistic Sequential Shrinking: A Best Arm Identification Algorithm for Stochastic Bandits with Corruptions
Zixin Zhong, Wang Chi Cheung, Vincent Tan
Poster
Tue 21:00 Probabilistic Sequential Shrinking: A Best Arm Identification Algorithm for Stochastic Bandits with Corruptions
Zixin Zhong, Wang Chi Cheung, Vincent Tan
Spotlight
Wed 5:25 Approximating a Distribution Using Weight Queries
Nadav Barak, Sivan Sabato
Spotlight
Wed 5:25 Adversarial Combinatorial Bandits with General Non-linear Reward Functions
Yanjun Han, Yining Wang, Xi Chen
Spotlight
Wed 6:45 An Algorithm for Stochastic and Adversarial Bandits with Switching Costs
Chloé Rouyer, Yevgeny Seldin, Nicolò Cesa-Bianchi
Oral
Wed 7:00 High-dimensional Experimental Design and Kernel Bandits
Romain Camilleri, Kevin Jamieson, Julian Katz-Samuels
Spotlight Session
Wed 7:00 Reinforcement Learning and Bandits
Oral Session
Wed 7:00 Bandits 1
Spotlight
Wed 7:20 Dichotomous Optimistic Search to Quantify Human Perception
Julien Audiffren
Spotlight
Wed 7:25 Improved Confidence Bounds for the Linear Logistic Model and Applications to Bandits
Kwang-Sung Jun, Lalit Jain, Blake Mason, Houssam Nassif
Spotlight
Wed 7:30 Stochastic Multi-Armed Bandits with Unrestricted Delay Distributions
Tal Lancewicki, Shahar Segal, Tomer Koren, Yishay Mansour
Spotlight
Wed 7:35 Deciding What to Learn: A Rate-Distortion Approach
Dilip Arumugam, Benjamin Van Roy
Spotlight
Wed 7:35 Best Model Identification: A Rested Bandit Formulation
Leonardo Cella, Massimiliano Pontil, Claudio Gentile
Spotlight
Wed 7:40 No-regret Algorithms for Capturing Events in Poisson Point Processes
Mojmir Mutny, Andreas Krause
Spotlight
Wed 7:45 Parametric Graph for Unimodal Ranking Bandit
CamilleS GAUTHIER, Romaric Gaudel, Elisa Fromont, Boammani Aser Lompo
Poster
Wed 9:00 Parametric Graph for Unimodal Ranking Bandit
CamilleS GAUTHIER, Romaric Gaudel, Elisa Fromont, Boammani Aser Lompo
Poster
Wed 9:00 Adversarial Combinatorial Bandits with General Non-linear Reward Functions
Yanjun Han, Yining Wang, Xi Chen
Poster
Wed 9:00 Approximating a Distribution Using Weight Queries
Nadav Barak, Sivan Sabato
Poster
Wed 9:00 Improved Confidence Bounds for the Linear Logistic Model and Applications to Bandits
Kwang-Sung Jun, Lalit Jain, Blake Mason, Houssam Nassif
Poster
Wed 9:00 Dichotomous Optimistic Search to Quantify Human Perception
Julien Audiffren
Poster
Wed 9:00 Stochastic Multi-Armed Bandits with Unrestricted Delay Distributions
Tal Lancewicki, Shahar Segal, Tomer Koren, Yishay Mansour
Poster
Wed 9:00 Best Model Identification: A Rested Bandit Formulation
Leonardo Cella, Massimiliano Pontil, Claudio Gentile
Poster
Wed 9:00 Deciding What to Learn: A Rate-Distortion Approach
Dilip Arumugam, Benjamin Van Roy
Poster
Wed 9:00 High-dimensional Experimental Design and Kernel Bandits
Romain Camilleri, Kevin Jamieson, Julian Katz-Samuels
Poster
Wed 9:00 An Algorithm for Stochastic and Adversarial Bandits with Switching Costs
Chloé Rouyer, Yevgeny Seldin, Nicolò Cesa-Bianchi
Poster
Wed 9:00 No-regret Algorithms for Capturing Events in Poisson Point Processes
Mojmir Mutny, Andreas Krause
Oral Session
Wed 17:00 Bandits 2
Oral
Wed 17:00 The Symmetry between Arms and Knapsacks: A Primal-Dual Approach for Bandits with Knapsacks
Xiaocheng Li, Chunlin Sun, Yinyu Ye
Spotlight
Wed 17:20 Dynamic Planning and Learning under Recovering Rewards
David Simchi-Levi, Zeyu Zheng, Feng Zhu
Spotlight
Wed 17:25 Best Arm Identification in Graphical Bilinear Bandits
Geovani Rizk, Albert Thomas, Igor Colin, Rida Laraki, Yann Chevaleyre
Spotlight
Wed 17:25 Confidence-Budget Matching for Sequential Budgeted Learning
Yonathan Efroni, Nadav Merlis, Aadirupa Saha, Shie Mannor
Spotlight
Wed 17:25 Adversarial Dueling Bandits
Aadirupa Saha, Tomer Koren, Yishay Mansour
Spotlight
Wed 17:30 Achieving Near Instance-Optimality and Minimax-Optimality in Stochastic and Adversarial Linear Bandits Simultaneously
Chung-Wei Lee, Haipeng Luo, Chen-Yu Wei, Mengxiao Zhang, Xiaojin Zhang
Spotlight
Wed 17:30 Near-Optimal Representation Learning for Linear Bandits and Linear RL
Jiachen Hu, Xiaoyu Chen, Chi Jin, Lihong Li, Liwei Wang
Spotlight
Wed 17:35 Incentivized Bandit Learning with Self-Reinforcing User Preferences
Tianchen Zhou, Jia Liu, Chaosheng Dong, jingyuan deng
Spotlight
Wed 17:40 Approximation Theory Based Methods for RKHS Bandits
Sho Takemori, Masahiro Sato
Spotlight
Wed 17:45 Dynamic Balancing for Model Selection in Bandits and RL
Ashok Cutkosky, Christoph Dann, Abhimanyu Das, Claudio Gentile, Aldo Pacchiano, Manish Purohit
Oral Session
Wed 18:00 Bandits 3
Oral
Wed 18:00 Resource Allocation in Multi-armed Bandit Exploration: Overcoming Sublinear Scaling with Adaptive Parallelism
Brijen Thananjeyan, Kirthevasan Kandasamy, Ion Stoica, Michael Jordan, Ken Goldberg, Joseph E Gonzalez
Spotlight
Wed 18:20 Optimal Streaming Algorithms for Multi-Armed Bandits
Tianyuan Jin, Keke Huang, Jing Tang, Xiaokui Xiao
Spotlight
Wed 18:25 Top-k eXtreme Contextual Bandits with Arm Hierarchy
Rajat Sen, Alexander Rakhlin, Lexing Ying, Rahul Kidambi, Dean Foster, Daniel Hill, Inderjit Dhillon
Spotlight
Wed 18:30 Improved Regret Bounds of Bilinear Bandits using Action Space Analysis
Kyoungseok Jang, Kwang-Sung Jun, Se-Young Yun, Wanmo Kang
Spotlight
Wed 18:35 Interaction-Grounded Learning
Tengyang Xie, John Langford, Paul Mineiro, Ida Momennejad
Spotlight
Wed 18:40 Almost Optimal Anytime Algorithm for Batched Multi-Armed Bandits
Tianyuan Jin, Jing Tang, Pan Xu, Keke Huang, Xiaokui Xiao, Quanquan Gu
Spotlight
Wed 18:45 Pure Exploration and Regret Minimization in Matching Bandits
Flore Sentenac, Jialin Yi, Clément Calauzènes, Vianney Perchet, Milan Vojnovic
Oral Session
Wed 19:00 Bandits 4
Oral
Wed 19:00 Multi-layered Network Exploration via Random Walks: From Offline Optimization to Online Learning
Xutong Liu, Jinhang Zuo, Xiaowei Chen, Wei Chen, John C. S. Lui
Spotlight
Wed 19:20 Combinatorial Blocking Bandits with Stochastic Delays
Alexia Atsidakou, Orestis Papadigenopoulos, Soumya Basu, Constantine Caramanis, Sanjay Shakkottai
Spotlight
Wed 19:25 Sparsity-Agnostic Lasso Bandit
Min-hwan Oh, Garud Iyengar, Assaf Zeevi
Spotlight
Wed 19:30 Quantile Bandits for Best Arms Identification
Mengyan Zhang, Cheng Soon Ong
Spotlight
Wed 19:35 Beyond $log^2(T)$ regret for decentralized bandits in matching markets
Soumya Basu, Karthik Abinav Sankararaman, Abishek Sankararaman
Spotlight
Wed 19:40 Robust Pure Exploration in Linear Bandits with Limited Budget
Ayya Alieva, Ashok Cutkosky, Abhimanyu Das
Spotlight
Wed 19:40 Massively Parallel and Asynchronous Tsetlin Machine Architecture Supporting Almost Constant-Time Scaling
Kuruge Darshana Abeyrathna, Bimal Bhattarai, Morten Goodwin, Saeed Rahimi Gorji, Ole-Christoffer Granmo, Lei Jiao, Rupsa Saha, Rohan Kumar Yadav
Spotlight
Wed 19:45 Adapting to misspecification in contextual bandits with offline regression oracles
Sanath Kumar Krishnamurthy, Vitor Hadad, Susan Athey
Poster
Wed 21:00 Combinatorial Blocking Bandits with Stochastic Delays
Alexia Atsidakou, Orestis Papadigenopoulos, Soumya Basu, Constantine Caramanis, Sanjay Shakkottai
Poster
Wed 21:00 Achieving Near Instance-Optimality and Minimax-Optimality in Stochastic and Adversarial Linear Bandits Simultaneously
Chung-Wei Lee, Haipeng Luo, Chen-Yu Wei, Mengxiao Zhang, Xiaojin Zhang
Poster
Wed 21:00 The Symmetry between Arms and Knapsacks: A Primal-Dual Approach for Bandits with Knapsacks
Xiaocheng Li, Chunlin Sun, Yinyu Ye
Poster
Wed 21:00 Confidence-Budget Matching for Sequential Budgeted Learning
Yonathan Efroni, Nadav Merlis, Aadirupa Saha, Shie Mannor
Poster
Wed 21:00 Robust Pure Exploration in Linear Bandits with Limited Budget
Ayya Alieva, Ashok Cutkosky, Abhimanyu Das
Poster
Wed 21:00 Dynamic Balancing for Model Selection in Bandits and RL
Ashok Cutkosky, Christoph Dann, Abhimanyu Das, Claudio Gentile, Aldo Pacchiano, Manish Purohit
Poster
Wed 21:00 Optimal Streaming Algorithms for Multi-Armed Bandits
Tianyuan Jin, Keke Huang, Jing Tang, Xiaokui Xiao
Poster
Wed 21:00 Best Arm Identification in Graphical Bilinear Bandits
Geovani Rizk, Albert Thomas, Igor Colin, Rida Laraki, Yann Chevaleyre
Poster
Wed 21:00 Almost Optimal Anytime Algorithm for Batched Multi-Armed Bandits
Tianyuan Jin, Jing Tang, Pan Xu, Keke Huang, Xiaokui Xiao, Quanquan Gu
Poster
Wed 21:00 Massively Parallel and Asynchronous Tsetlin Machine Architecture Supporting Almost Constant-Time Scaling
Kuruge Darshana Abeyrathna, Bimal Bhattarai, Morten Goodwin, Saeed Rahimi Gorji, Ole-Christoffer Granmo, Lei Jiao, Rupsa Saha, Rohan Kumar Yadav
Poster
Wed 21:00 Sparsity-Agnostic Lasso Bandit
Min-hwan Oh, Garud Iyengar, Assaf Zeevi
Poster
Wed 21:00 Adapting to misspecification in contextual bandits with offline regression oracles
Sanath Kumar Krishnamurthy, Vitor Hadad, Susan Athey
Poster
Wed 21:00 Top-k eXtreme Contextual Bandits with Arm Hierarchy
Rajat Sen, Alexander Rakhlin, Lexing Ying, Rahul Kidambi, Dean Foster, Daniel Hill, Inderjit Dhillon
Poster
Wed 21:00 Approximation Theory Based Methods for RKHS Bandits
Sho Takemori, Masahiro Sato
Poster
Wed 21:00 Improved Regret Bounds of Bilinear Bandits using Action Space Analysis
Kyoungseok Jang, Kwang-Sung Jun, Se-Young Yun, Wanmo Kang
Poster
Wed 21:00 Quantile Bandits for Best Arms Identification
Mengyan Zhang, Cheng Soon Ong
Poster
Wed 21:00 Pure Exploration and Regret Minimization in Matching Bandits
Flore Sentenac, Jialin Yi, Clément Calauzènes, Vianney Perchet, Milan Vojnovic
Poster
Wed 21:00 Resource Allocation in Multi-armed Bandit Exploration: Overcoming Sublinear Scaling with Adaptive Parallelism
Brijen Thananjeyan, Kirthevasan Kandasamy, Ion Stoica, Michael Jordan, Ken Goldberg, Joseph E Gonzalez
Poster
Wed 21:00 Incentivized Bandit Learning with Self-Reinforcing User Preferences
Tianchen Zhou, Jia Liu, Chaosheng Dong, jingyuan deng
Poster
Wed 21:00 Beyond $log^2(T)$ regret for decentralized bandits in matching markets
Soumya Basu, Karthik Abinav Sankararaman, Abishek Sankararaman
Poster
Wed 21:00 Adversarial Dueling Bandits
Aadirupa Saha, Tomer Koren, Yishay Mansour
Poster
Wed 21:00 Near-Optimal Representation Learning for Linear Bandits and Linear RL
Jiachen Hu, Xiaoyu Chen, Chi Jin, Lihong Li, Liwei Wang
Poster
Wed 21:00 Interaction-Grounded Learning
Tengyang Xie, John Langford, Paul Mineiro, Ida Momennejad
Poster
Wed 21:00 Dynamic Planning and Learning under Recovering Rewards
David Simchi-Levi, Zeyu Zheng, Feng Zhu
Poster
Wed 21:00 Multi-layered Network Exploration via Random Walks: From Offline Optimization to Online Learning
Xutong Liu, Jinhang Zuo, Xiaowei Chen, Wei Chen, John C. S. Lui
Spotlight
Thu 6:25 Off-Policy Confidence Sequences
Nikos Karampatziakis, Paul Mineiro, Aaditya Ramdas
Spotlight
Thu 7:35 Online Limited Memory Neural-Linear Bandits with Likelihood Matching
Ofir Nabati, Tom Zahavy, Shie Mannor
Poster
Thu 9:00 Off-Policy Confidence Sequences
Nikos Karampatziakis, Paul Mineiro, Aaditya Ramdas
Poster
Thu 9:00 Online Limited Memory Neural-Linear Bandits with Likelihood Matching
Ofir Nabati, Tom Zahavy, Shie Mannor
Poster
Thu 9:00 Adapting to Delays and Data in Adversarial Multi-Armed Bandits
András György, Pooria Joulani
Spotlight
Thu 18:30 Meta-Thompson Sampling
Branislav Kveton, Mikhail Konobeev, Manzil Zaheer, Chih-wei Hsu, Martin Mladenov, Craig Boutilier, Csaba Szepesvari
Spotlight Session
Thu 20:30 Bandits 5
Spotlight
Thu 20:30 Lenient Regret and Good-Action Identification in Gaussian Process Bandits
Xu Cai, Selwyn Gomes, Jonathan Scarlett
Spotlight
Thu 20:30 On Lower Bounds for Standard and Robust Gaussian Process Bandit Optimization
Xu Cai, Jonathan Scarlett
Spotlight
Thu 20:35 Optimal Thompson Sampling strategies for support-aware CVaR bandits
Dorian Baudry, Romain Gautron, Emilie Kaufmann, Odalric-Ambrym Maillard
Spotlight
Thu 20:40 On Limited-Memory Subsampling Strategies for Bandits
Dorian Baudry, Yoan Russac, Olivier Cappé
Spotlight
Thu 20:45 Problem Dependent View on Structured Thresholding Bandit Problems
James Cheshire, Pierre MENARD, Alexandra Carpentier
Spotlight
Thu 20:50 Leveraging Good Representations in Linear Contextual Bandits
Matteo Papini, Andrea Tirinzoni, Marcello Restelli, Alessandro Lazaric, Matteo Pirotta
Poster
Thu 21:00 Optimal Thompson Sampling strategies for support-aware CVaR bandits
Dorian Baudry, Romain Gautron, Emilie Kaufmann, Odalric-Ambrym Maillard
Poster
Thu 21:00 On Lower Bounds for Standard and Robust Gaussian Process Bandit Optimization
Xu Cai, Jonathan Scarlett
Poster
Thu 21:00 Problem Dependent View on Structured Thresholding Bandit Problems
James Cheshire, Pierre MENARD, Alexandra Carpentier
Poster
Thu 21:00 On Limited-Memory Subsampling Strategies for Bandits
Dorian Baudry, Yoan Russac, Olivier Cappé
Poster
Thu 21:00 Leveraging Good Representations in Linear Contextual Bandits
Matteo Papini, Andrea Tirinzoni, Marcello Restelli, Alessandro Lazaric, Matteo Pirotta
Poster
Thu 21:00 Lenient Regret and Good-Action Identification in Gaussian Process Bandits
Xu Cai, Selwyn Gomes, Jonathan Scarlett
Poster
Thu 21:00 Meta-Thompson Sampling
Branislav Kveton, Mikhail Konobeev, Manzil Zaheer, Chih-wei Hsu, Martin Mladenov, Craig Boutilier, Csaba Szepesvari
Workshop
Fri 9:45 Sequential Automated Machine Learning: Bandits-driven Exploration using a Collaborative Filtering Representation
Maxime Heuillet
Workshop
Fri 11:00 Poster session 2
Workshop
Fri 13:41 Designing Bounded min-knapsack Bandits algorithm for Sustainable Demand Response
Akansha Singh
Workshop
Sat 15:30 Solving Multi-Arm Bandit Using a Few Bits of Communication
Osama Hanna, Lin Yang, Christina Fragouli
Workshop
Poster: Designing Bounded min-knapsack Bandits algorithm for Sustainable Demand Response
Workshop
Sequential Automated Machine Learning: Bandits-driven Exploration using a Collaborative Filtering Representation
Maxime Heuillet, Benoit Debaque, Audrey Durand
Workshop
Collision Resolution in Multi-player Bandits Without Observing Collision Information
Eleni Nisioti, Nikolaos Thomos, Boris Bellalta, Anders Jonsson
Workshop
Learning from an Exploring Demonstrator: Optimal Reward Estimation for Bandits
Wenshuo Guo, Kumar Agrawal, Aditya Grover, Vidya Muthukumar, Ashwin Pananjady
Workshop
Invariant Policy Learning: A Causal Perspective
Sorawit Saengkyongam, Nikolaj Thams, Jonas Peters, Niklas Pfister
Workshop
Estimating Optimal Policy Value in Linear Contextual Bandits beyond Gaussianity
Jonathan Lee, Weihao Kong, Aldo Pacchiano, Vidya Muthukumar, Emma Brunskill
Workshop
A Short Note on the Relationship of Information Gain and Eluder Dimension
Kaixuan Huang, Sham Kakade, Jason Lee, Qi Lei
Workshop
Non-Stationary Representation Learning in Sequential Multi-Armed Bandits
Qin Yuzhen, Tommaso Menara, Samet Oymak, ShiNung Ching, Fabio Pasqualetti
Workshop
Designing Online Advertisements via Bandit and Reinforcement Learning
Richard Liu, Yusuke Narita, Kohei Yata
Workshop
Optimizing Dynamic Treatment Regimes via Volatile Contextual Gaussian Process Bandits
Ahmet Alparslan Celik, Cem Tekin
Workshop
Explaining Algorithm Aversion with Metacognitive Bandits
Aakriti Kumar
Workshop
Learning from an Exploring Demonstrator: Optimal Reward Estimation for Bandits
Wenshuo Guo
Workshop
Robust Generalization of Quadratic Neural Networks via Function Identification
Kan Xu, Hamsa Bastani, Osbert Bastani
Workshop
Hierarchical Imitation Learning with Contextual Bandits for DynamicTreatment Regimes
Lu Wang, Wenchao Yu, Wei Cheng, Bo Zong, Haifeng Chen
Workshop
Under-exploring in Bandits with Confounded Data
Nihal Sharma, Soumya Basu, Karthikeyan Shanmugam, Sanjay Shakkottai
Workshop
Solving Multi-Arm Bandit Using a Few Bits of Communication
Osama Hanna, Lin Yang, Christina Fragouli