"Directivity Modes of Earthquake Populations with Unsupervised Learning "[link]
- By Zachary E Ross, Daniel T Trugman, Kamyar Azizzadenesheli, Anima Anandkumar
"Maybe a few considerations in Reinforcement Learning Research?" [link]
- By Kamyar Azizzadenesheli
"Learning Causal State Representations of Partially Observable Environments"[link]
- By Amy Zhang, Zachary C Lipton, Luis Pineda, Kamyar Azizzadenesheli, Anima Anandkumar, Laurent Itti, Joelle Pineau, Tommaso Furlanello
"Trust Region Policy Optimization of POMDPs" [link]
- By Kamyar Azizzadenesheli, Manish Kumar Bera, Animashree Anandkumar.
"Stochastic Linear Bandits with Hidden Low Rank Structure"[link]
- By Sahin Lale, Kamyar Azizzadenesheli, Animashree Anandkumar, Babak Hassibi
"signSGD with Majority Vote is Communication Efficient and Byzantine Fault Tolerant" [link]
- By Jeremy Bernstein, Yu-Xiang Wang, Kamyar Azizzadenesheli, Anima Anandkumar
Appeared at International Conference on Learning Representations (ICLR) 2019
"Surprising Negative Results for Generative Adversarial Tree Search" [link]
- By Kamyar Azizzadenesheli, Brandon Yang, Weitang Liu, Emma Brunskill , Zachary C. Lipton, Animashree Anandkumar
Appeared at Neural Information Processing Systems (NeurIPS) 2018 Workshop
"signSGD: compressed optimisation for non-convex problems" [link]
- By Jeremy Bernstein, Yu-Xiang Wang, Kamyar Azizzadenesheli, Anima Anandkumar
Appeared at International Conference on Machine Learning (ICML) 2018
"Compression by the signs: distributed learning is a two-way street" [link]
- By Jeremy Bernstein, Yu-Xiang Wang, Kamyar Azizzadenesheli, Anima Anandkumar
Appeared at International Conference on Learning Representations (ICLR) 2018 Workshop
"Stochastic activation pruning for robust adversarial defense" [link]
- By Guneet S. Dhillon, Kamyar Azizzadenesheli, Jeremy D. Bernstein, Jean Kossaifi, Aran Khanna, Zachary C. Lipton, Animashree Anandkumar
Appeared at International Conference on Learning Representations (ICLR) 2018
"Reinforcement Learning in Rich-Observation MDPs using Spectral Methods" [link]
- By Kamyar Azizzadenesheli, Alessandro Lazaric, Anima Anandkumar
Appeared at Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM) 2017
Ph.D. Thesis:
"Reinforcement Learning in Structured and Partially Observable Environments" [link]
- By Kamyar Azizzadenesheli