Segui
Akshay Krishnamurthy
Akshay Krishnamurthy
Email verificata su cs.umass.edu - Home page
Titolo
Citata da
Citata da
Anno
Deep batch active learning by diverse, uncertain gradient lower bounds
JT Ash, C Zhang, A Krishnamurthy, J Langford, A Agarwal
arXiv preprint arXiv:1906.03671, 2019
8372019
Go for a walk and arrive at the answer: Reasoning over paths in knowledge bases using reinforcement learning
R Das, S Dhuliawala, M Zaheer, L Vilnis, I Durugkar, A Krishnamurthy, ...
arXiv preprint arXiv:1711.05851, 2017
6412017
Contextual decision processes with low bellman rank are pac-learnable
N Jiang, A Krishnamurthy, A Agarwal, J Langford, RE Schapire
International Conference on Machine Learning, 1704-1713, 2017
5032017
Parallelised Bayesian optimisation via Thompson sampling
K Kandasamy, A Krishnamurthy, J Schneider, B Póczos
International conference on artificial intelligence and statistics, 133-142, 2018
331*2018
Flambe: Structural complexity and representation learning of low rank mdps
A Agarwal, S Kakade, A Krishnamurthy, W Sun
Advances in neural information processing systems 33, 20095-20107, 2020
2922020
Provably efficient rl with rich observations via latent state decoding
S Du, A Krishnamurthy, N Jiang, A Agarwal, M Dudik, J Langford
International Conference on Machine Learning, 1665-1674, 2019
2792019
Model-based rl in contextual decision processes: Pac bounds and exponential improvements over model-free approaches
W Sun, N Jiang, A Krishnamurthy, A Agarwal, J Langford
Conference on learning theory, 2898-2933, 2019
2772019
Reward-free exploration for reinforcement learning
C Jin, A Krishnamurthy, M Simchowitz, T Yu
International Conference on Machine Learning, 4870-4879, 2020
2612020
Learning to search better than your teacher
KW Chang, A Krishnamurthy, A Agarwal, J Langford, H Daumé III
International Conference on Machine Learning, 2015, 2015
2372015
Off-policy evaluation for slate recommendation
A Swaminathan, A Krishnamurthy, A Agarwal, M Dudik, J Langford, ...
Advances in Neural Information Processing Systems 30, 2017
2342017
Kinematic state abstraction and provably efficient rich-observation reinforcement learning
D Misra, M Henaff, A Krishnamurthy, J Langford
International conference on machine learning, 6961-6971, 2020
1962020
Low-rank matrix and tensor completion via adaptive sampling
A Krishnamurthy, A Singh
Advances in neural information processing systems 26, 2013
1962013
Pac reinforcement learning with rich observations
A Krishnamurthy, A Agarwal, J Langford
Advances in Neural Information Processing Systems 29, 2016
1952016
Optimism in reinforcement learning with generalized linear function approximation
Y Wang, R Wang, SS Du, A Krishnamurthy
arXiv preprint arXiv:1912.04136, 2019
1812019
Contrastive learning, multi-view redundancy, and linear models
C Tosh, A Krishnamurthy, D Hsu
Algorithmic Learning Theory, 1179-1206, 2021
1702021
Transformers learn shortcuts to automata
B Liu, JT Ash, S Goel, A Krishnamurthy, C Zhang
arXiv preprint arXiv:2210.10749, 2022
1572022
Information theoretic regret bounds for online nonlinear control
S Kakade, A Krishnamurthy, K Lowrey, M Ohnishi, W Sun
Advances in Neural Information Processing Systems 33, 15312-15325, 2020
1442020
On oracle-efficient pac rl with rich observations
C Dann, N Jiang, A Krishnamurthy, A Agarwal, J Langford, RE Schapire
Advances in neural information processing systems 31, 2018
1382018
DEGAS: de novo discovery of dysregulated pathways in human diseases
I Ulitsky, A Krishnamurthy, RM Karp, R Shamir
PloS one 5 (10), e13367, 2010
1362010
Nonparametric von mises estimators for entropies, divergences and mutual informations
K Kandasamy, A Krishnamurthy, B Poczos, L Wasserman
Advances in Neural Information Processing Systems 28, 2015
1322015
Il sistema al momento non può eseguire l'operazione. Riprova più tardi.
Articoli 1–20