Publications

Bo Dai, "Learning over Functions, Distributions and Dynamics via Stochastic Optimization". PhD Thesis, August 2018.

Hongyu Ren, Hanjun Dai, Zihang Dai, Mengjiao Yang, Jure Leskovec, Dale Schuurmans, Bo Dai. "Combiner: Full Attention Transformer with Sparse Computation Cost". Neural Information Processing Systems (NeurIPS'2021).

Tongzheng Ren, Jialian Li, Bo Dai, Simon S Du, Sujay Sanghavi. "Nearly Horizon-Free Offline Reinforcement Learning". Neural Information Processing Systems (NeurIPS'2021).

Jincheng Mei, Bo Dai, Chenjun Xiao, Csaba Szepesvari, Dale Schuurmans. "Understanding the Effect of Stochasticity in Policy Optimization". Neural Information Processing Systems (NeurIPS'2021).

Ruoxi Sun, Hanjun Dai, Li Li, Stevens Kearnes, Bo Dai. "Towards Understanding Retrosynthesis by Energy-Based Models". Neural Information Processing Systems (NeurIPS'2021).

Haoming Jiang, Bo Dai, Mengjiao Yang, Tuo Zhao and Wei Wei. "Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach". Conference on Empirical Methods in Natural Language Processing (EMNLP'2021)

Jincheng Mei, Yue Gao, Bo Dai, Csaba Szepesvari, Dale Schuurmans. "Leveraging Non-uniformity in First-order Non-convex Optimization". The 38th International Conference on Machine Learning (ICML'2021).

Pei-Hung Chen, Wei Wei, Cho-Jui Hsieh, Bo Dai. "Overcoming Catastrophic Forgetting by Bayesian Generative Regularization". The 38th International Conference on Machine Learning (ICML'2021).

Chenjun Xiao, Yifan Wu, Tor Lattimore, Bo Dai, Jincheng Mei, Lihong Li, Csaba Szepesvari, Dale Schuurmans. "On the Optimality of Batch Policy Optimization Algorithms". The 38th International Conference on Machine Learning (ICML'2021).

Hongyu Ren, Hanjun Dai, Bo Dai, Xinyun Chen, Michihiro Yasunaga, Haitian Sun, Dale Schuurmans, Jure Leskovec, Denny Zhou. "LEGO: Latent Execution-Guided Reasoning for Multi-Hop Question Answering on Knowledge Graphs". The 38th International Conference on Machine Learning (ICML'2021).

Haoming Jiang, Zhehui Chen, Yuyang Shi, Bo Dai, Tuo Zhao. "Learning to Defend by Learning to Attack". The 24th International Conference on Artificial Intelligence and Statistics (AISTATS'2021).

Bo Dai*, Ofir Nachum*, Yinlam Chow, Lihong Li, Csaba Szepesvari, Dale Schuurmans. "CoinDICE: Off-Policy Confidence Interval Estimation". Neural Information Processing Systems (Spotlight, NeurIPS'2020).

Jincheng Mei, Chenjun Xiao, Bo Dai, Lihong Li, Csaba Szepesvari, Dale Schuurmans. "Escaping the gravitational pull of softmax". Neural Information Processing Systems (Oral, NeurIPS'2020).

Mengjiao Yang, Ofir Nachum, Bo Dai, Lihong Li, Dale Schuurmans. "Off-Policy Evaluation via the Regularized Lagrangian". Neural Information Processing Systems (NeurIPS'2020).

Hanjun Dai, Rishabh Singh, Bo Dai, Charles Sutton, Dale Schuurmans. "Learning Discrete Energy-based Models via Auxiliary-variable Local Exploration". Neural Information Processing Systems (NeurIPS'2020).

Luofeng Liao, You-Lin Chen, Zhuoran Yang, Bo Dai, Mladen Kolar, Zhaoran Wang. "Provably Efficient Neural Estimation of Structural Equation Models: An Adversarial Approach". Neural Information Processing Systems (NeurIPS'2020).

Zhuangdi Zhu, Kaixiang Lin, Bo Dai, Jiayu Zhou. "Off-Policy Imitation Learning from Observations". Neural Information Processing Systems (NeurIPS'2020).

Yujia Xie, Hanjun Dai, Minshuo Chen, Bo Dai, Tuo Zhao, Hongyuan Zha, Wei Wei, Tomas Pfister. "Differentiable Top-k Operator with Optimal Transport". Neural Information Processing Systems (NeurIPS'2020).

Junfeng Wen*, Bo Dai*, Lihong Li, Dale Schuurmans. "Batch Stationary Distribution Estimation". The 37th International Conference on Machine Learning (ICML'2020).

Mengjiao Yang*, Bo Dai*, Hanjun Dai, Dale Schuurmans. "Energy-Based Processes for Exchangeable Data". The 37th International Conference on Machine Learning (ICML'2020).

Hanjun Dai, Azade Nazi, Yujia Li, Bo Dai, Dale Schuurmans. "Scalable Deep Generative Modeling for Sparse Graphs". The 37th International Conference on Machine Learning (ICML'2020).

Ruiyi Zhang*, Bo Dai*, Lihong Li, Dale Schuurmans. "GenDICE: Generalized Offline Estimation of Stationary Values. " The 8th International Conference on Learning Representations (Oral, ICLR'2020).

Binghong Chen*, Bo Dai*, Qinjie Lin, Guo Ye, Han Liu, Le Song. "Learning to Plan in High Dimensions via Neural Exploration-Exploitation Trees". The 8th International Conference on Learning Representations (Spotlight, ICLR'2020).

Bo Dai*, Zhen Liu*, Hanjun Dai*, Niao He, Arthur Gretton, Le Song, Dale Schuurmans. "Exponential Family Estimation via Adversarial Dynamics Embedding". Neural Information Processing Systems (NeurIPS'2019).[CODE]

Hanjun Dai, Chengtao Li, Connor Coley, Bo Dai, Le Song. "Retrosynthesis Prediction with Conditional Graph Logic Network". Neural Information Processing Systems (NeurIPS'2019).[CODE]

Ofir Nachum*, Yinlam Chow*, Bo Dai, Lihong Li. "DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections". Neural Information Processing Systems (spotlight, NeurIPS'2019).[CODE]

Dieterich Lawson*, George Tucker*, Bo Dai, Rajesh Ranganath. "Energy-Inspired Models: Learning with Sampler-Induced Distributions". Neural Information Processing Systems (NeurIPS'2019). [CODE]

Albert Shaw, Wei Wei, Weiyang Liu, Le Song, Bo Dai. "Meta Architecture Search". Neural Information Processing Systems (NeurIPS'2019).[CODE]

Bo Dai*, Hanjun Dai*, Arthur Gretton, Le Song, Dale Schuurmans, Niao He. "Kernel Exponential Family Estimation via Doubly Dual Embedding". The 22nd International Conference on Artificial Intelligence and Statistics (AISTATS'2019). [CODE]

Bo Dai*, Hanjun Dai*, Niao He, Weiyang Liu, Zhen Liu, Jianshu Chen, Lin Xiao, Le Song. "Coupled Variational Bayes via Optimization Embedding". Neural Information Processing Systems (NeurIPS'2018). [CODE]

Yingxiang Yang, Bo Dai, Negar Kiyavash, Niao He. "Predictive Approximate Bayesian Computation via Saddle Points". Neural Information Processing Systems (NeurIPS'2018).

Weiyang Liu, Rongmei Lin, Zhen Liu, Lixin Liu, Zhiding Yu, Bo Dai, Le Song. "Learning towards Minimum Hyperspherical Energy". Neural Information Processing Systems (NeurIPS'2018).

Harsh Shrivastava, Eugene Bart, Bob Price, Hanjun Dai, Bo Dai, Srinivas Aluru. "Cooperative neural networks (CoNN): Exploiting prior independence structure for improved classification". Neural Information Processing Systems (NeurIPS'2018).

Bo Dai, Albert Shaw, Lihong Li, Lin Xiao, Niao He, Zhen Liu, Jianshu Chen, Le Song. "SBEED: Convergent Reinforcement Learning with Nonlinear Function Approximation". The 35th International Conference on Machine Learning (long talk, ICML'2018).

Weiyang Liu*, Bo Dai*, Xingguo Li, Zhen Liu, James Rehg, Le Song. "Towards Black-box Iterative Machine Teaching". The 35th International Conference on Machine Learning (ICML'2018).

Hanjun Dai, Zornitsa Kozareva, Bo Dai, Alexander Smola and Le Song. "Learning Steady-States of Iterative Algorithms over Graphs". The 35th International Conference on Machine Learning (ICML'2018). [CODE]

Bo Dai*, Albert Shaw*, Niao He, Lihong Li, Le Song. "Boosting the Actor with Dual Critic". The 6th International Conference on Learning Representations (ICLR'2018).

Hanjun Dai, Yingtao Tian, Bo Dai, Steven Skiena, Le Song. "Syntax-Directed Variational Autoencoder for Structured Data". The 6th International Conference on Learning Representations (ICLR'2018).

Weiyang Liu*, Zhen Liu*, Zhiding Yu, Bo Dai, Rongmei Lin, Yisen Wang, James M. Rehg, Le Song. "Decoupled Networks". The 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition (spotlight, CVPR'2018)

Woosang Lim, Rundong Du, Bo Dai, Kyomin Jung, Le Song, Haesun Park. "Multi-scale Nystrom Method". The 21st International Conference on Artificial Intelligence and Statistics (full oral presentation, AISTATS'2018).

Bo Dai*, Ruiqi Guo*, Sanjiv Kumar, Niao He, and Le Song. "Stochastic Generative Hashing". The 34th International Conference on Machine Learning (ICML'2017). [CODE]

Weiyang Liu, Bo Dai, James M. Rehg, and Le Song. "Iterative Machine Teaching". The 34th International Conference on Machine Learning (ICML'2017).

Bo Dai, Niao He, Yunpeng Pan, Byron Boots, and Le Song. "Learning from Conditional Distributions via Dual Embeddings". The 20th International Conference on Artificial Intelligence and Statistics (AISTATS'2017).

Weiyang Liu, Yan-Ming Zhang, Xingguo Li, Zhiding Yu, Bo Dai, Tuo Zhao, and Le Song. "Deep Hyperspherical Learning". Neural Information Processing Systems (spotlight, NIPS' 2017).

Hanjun Dai, Bo Dai, Yan-Ming Zhang, Shuang Li and Le Song. "Recurrent Hidden Semi-Markov Model". The 5th International Conference on Learning Representations (ICLR'2017).

Hanjun Dai, Bo Dai and Le Song. "Discriminative Embeddings of Latent Variable Models for Structured Data". The 33th International Conference on Machine Learning (ICML'2016). [CODE]

Bo Dai, Niao He, Hanjun Dai and Le Song. "Provable Bayesian Inference via Particle Mirror Descent", The 19th International Conference on Artificial Intelligence and Statistics (Best Student Paper Award, full oral presentation, AISTATS'2016).

Bo Dai, Bo Xie, Niao He, Yingyu Liang, Anant Raj, Maria-Florina Balcan and Le Song. "Scalable Kernel Methods via Doubly Stochastic Gradients", Neural Information Processing Systems (NIPS'2014). [CODE]

Le Song, Animashree Anandkumar, Bo Dai and Bo Xie. "Nonparametric Estimation of Multi-View Latent Variable Models". The 31th International Conference on Machine Learning (ICML'2014). [CODE]

Gang Niu, Bo Dai, Marthinus Christoffel du Plessis and Masashi Sugiyama. "Transductive Learning with Multi-class Volume Approximation". The 31th International Conference on Machine Learning (ICML'2014).

Le Song and Bo Dai. "Robust Low Rank Kernel Embedding of Multivariate Distributions". Neural Information Processing Systems (NIPS'2013).

Gang Niu, Wittawat Jitkrittum, Bo Dai, Hirotaka Hachiya, and Masashi Sugiyama. "Squared-loss Mutual Information Regularization: A novel information-theoretic approach to semi-supervised learning". The 30th International Conference on Machine Learning (ICML'2013).

Gang Niu, Bo Dai, Makoto Yamada and Masashi Sugiyama. "Information-theoretic Semi-supervised Metric Learning via Entropy Regularization". The 29th International Conference on Machine Learning (ICML'2012).

Gang Niu, Bo Dai, Lin Shang and Masashi Sugiyama. "Maximum Volume Clustering". The 14th International Conference on Artificial Intelligence and Statistics (AISTATS'2011).

Bo Dai, Baogang Hu and Gang Niu. "Bayesian Maximum Margin Clustering". The 10th IEEE International Conference on Data Mining (full oral presentation, ICDM'2010).

Bo Dai and Baogang Hu. "Minimum Conditional Entropy Clustering: A Discriminative Framework of Clustering". JMLR: Workshop and Conference Proceedings (ACML'2010).

Bo Dai and Gang Niu. "Compact Margin Machine", The 14th Pacific-Asian Conference on Knowledge Discovery and Data Mining (PAKDD'2010).

Gang Niu, Bo Dai, Lin Shang and Yangsheng Ji. "Rough Margin based Core Vector Machines", The 14th Pacific-Asian Conference on Knowledge Discovery and Data Mining (PAKDD'2010).

Yajun Qu, Bo Dai and Baogang Hu. "Neural-network Based Regression Model with Prior from Ranking Information", International Joint Conference on Neural Networks (IJCNN'2010).

Gang Niu, Bo Dai, Makoto Yamada, and Masashi Sugiyama. "Information-theoretic semi-supervised metric learning via entropy regularization." Neural Computation 26, 1717–1762 (2014).

Gang Niu, Bo Dai, Lin Shang, and Masashi Sugiyama. "Maximum volume clustering: A new discriminative clustering approach". Journal of Machine Learning Research, vol. 14 (Sep) , pp. 2614--2687, 2013.

Bo Dai, Hanjun Dai, Niao He, Arthur Gretton, Le Song, Dale Schuurmans. "Exponential Family Estimation via Dynamics Embedding". NIPS 2018 Bayesian Deep Learning Workshop.

Albert Shaw*, Bo Dai*, Weiyang Liu, Le Song. "Bayesian Meta-network Architecture Learning". NIPS 2018 Bayesian Deep Learning Workshop.

Bo Dai, Albert Shaw, Lihong Li, Lin Xiao, Niao He, Jianshu Chen, Le Song. "Smoothed Dual Embedding Control". NIPS 2017 Deep Reinforcement Learning Symposium.

Bo Dai, Niao He, Yunpeng Pan, Byron Boots, and Le Song. "Learning from Conditional Distributions via Dual Embeddings". NIPS 2017 Learning on Distributions, Functions, Graphs and Groups Workshop.

Hanjun Dai, Yingtao Tian, Bo Dai, Steven Skiena, Le Song. "Syntax-Directed Variational Autoencoder for Molecule Generation". NIPS 2017 Machine Learning for Molecules and Materials Workshop (Best Paper Award).

Yunpeng Pan, Xinyan Yan, Bo Dai, Le Song, Evangelos Theodorou, Byron Boots. "Solving the Linear Bellman Equation via Kernel Embeddings and Stochastic Gradient Descent", NIPS 2016 Adaptive and Scalable Nonparametric Methods in Machine Learning Workshop.

Bo Dai, Niao He, Hanjun Dai, Le Song. "Provable Nonparametric Bayesian Inference", NIPS 2015 Advances in Approximate Bayesian Inference Workshop.