Kamyar Azizzadenesheli
Kamyar Azizzadenesheli
Postdoctoral fellow at Caltech
Verified email at caltech.edu - Homepage
TitleCited byYear
Stochastic activation pruning for robust adversarial defense
GS Dhillon, K Azizzadenesheli, ZC Lipton, J Bernstein, J Kossaifi, ...
International Conference on Learning Representations (ICLR) 2018, 2018
1242018
signSGD: compressed optimisation for non-convex problems
J Bernstein, YX Wang, K Azizzadenesheli, A Anandkumar
International Conference on Machine Learning (ICML) 2018, 2018
752018
Efficient Exploration through Bayesian Deep Q-Networks
K Azizzadenesheli, A Anandkumar
Neural Information Processing Systems (NIPS) 2017 Workshop, 2018
502018
Reinforcement learning of POMDPs using spectral methods
K Azizzadenesheli, A Lazaric, A Anandkumar
29th Annual Conference on Learning Theory (COLT) 2016, 2016
442016
Combating Reinforcement Learning's Sisyphean Curse with Intrinsic Fear
ZC Lipton, K Azizzadenesheli, A Kumar, L Li, J Gao, L Deng
Neural Information Processing Systems (NIPS) 2016 Workshop, 2016
43*2016
Neural Lander: Stable Drone Landing Control using Learned Dynamics
G Shi, X Shi, M O'Connell, R Yu, K Azizzadenesheli, A Anandkumar, ...
International Conference on Robotics and Automation (ICRA) 2019, 2018
212018
Surprising Negative Results for Generative Adversarial Tree Search
K Azizzadenesheli, B Yang, W Liu, Z Lipton, A Anandkumar
Neural Information Processing Systems (NeurIPS) 2018 Workshop, 2018
16*2018
Reinforcement learning in rich-observation MDPs using spectral methods
K Azizzadenesheli, A Lazaric, A Anandkumar
Multi-disciplinary Conference on Reinforcement Learning and Decision Making …, 2016
142016
Regularized Learning for Domain Adaptation under Label Shifts
K Azizzadenesheli, A Liu, F Yang, A Anandkumar
International Conference on Learning Representations (ICLR) 2018, 2018
102018
signSGD with Majority Vote is Communication Efficient and Fault Tolerant
J Bernstein, J Zhao, K Azizzadenesheli, A Anandkumar
International Conference on Learning Representations (ICLR) 2019, 2018
9*2018
Open problem: Approximate planning of POMDPs in the class of memoryless policies
K Azizzadenesheli, A Lazaric, A Anandkumar
Conference on Learning Theory (COLT) 2016, 1639-1642, 1639-1642, 2016
52016
Maybe a few considerations in Reinforcement Learning Research?
K Azizzadenesheli
42019
Stochastic Linear Bandits with Hidden Low Rank Structure
S Lale, K Azizzadenesheli, A Anandkumar, B Hassibi
arXiv preprint arXiv:1901.09490, 2019
42019
Experimental results: Reinforcement Learning of POMDPs using Spectral Methods
K Azizzadenesheli, A Lazaric, A Anandkumar
Neural Information Processing Systems (NIPS) 2016 Workshop, 2017
42017
Trust Region Policy Optimization for POMDPs
K Azizzadenesheli, MK Bera, A Anandkumar
arXiv preprint arXiv:1810.07900, 2018
22018
Learning Causal State Representations of Partially Observable Environments
A Zhang, ZC Lipton, L Pineda, K Azizzadenesheli, A Anandkumar, L Itti, ...
arXiv preprint arXiv:1906.10437, 2019
12019
Compression by the signs: distributed learning is a two-way street
J Bernstein, YX Wang, K Azizzadenesheli, A Anandkumar
12018
Directivity Modes of Earthquake Populations with Unsupervised Learning
ZE Ross, DT Trugman, K Azizzadenesheli, A Anandkumar
arXiv preprint arXiv:1907.00496, 2019
2019
Reinforcement Learning of Contextual MDPs using Spectral Methods
K Azizzadenesheli, A Lazaric, A Anandkumar
Multi-disciplinary Conference on Reinforcement Learning and Decision Making …, 2018
2018
The system can't perform the operation now. Try again later.
Articles 1–19