Prati
Rahul Kidambi
Rahul Kidambi
Amazon Search
Potvrđena adresa e-pošte na uw.edu - Početna stranica
Naslov
Citirano
Citirano
Godina
MOReL: Model-based Offline Reinforcement Learning
R Kidambi, A Rajeswaran, P Netrapalli, T Joachims
Conference on Neural Information Processing Systems (NeurIPS), 2020, 2020
3522020
Parallelizing stochastic gradient descent for least squares regression: mini-batching, averaging, and model misspecification
P Jain, SM Kakade, R Kidambi, P Netrapalli, A Sidford
Journal of Machine Learning Research (JMLR), 2018, 2018
155*2018
Accelerating stochastic gradient descent for least squares regression
P Jain, SM Kakade, R Kidambi, P Netrapalli, A Sidford
Conference On Learning Theory (COLT), 2018, 2018
1402018
The step decay schedule: A near optimal, geometrically decaying learning rate procedure
R Ge, SM Kakade, R Kidambi, P Netrapalli
Conference on Neural Information Processing Systems (NeurIPS), 2019, 2019
111*2019
On the insufficiency of existing momentum schemes for Stochastic Optimization
R Kidambi, P Netrapalli, P Jain, SM Kakade
International Conference on Learning Representations (ICLR), 2018, 2018
972018
A markov chain theory approach to characterizing the minimax optimality of stochastic gradient descent (for least squares)
P Jain, SM Kakade, R Kidambi, P Netrapalli, VK Pillutla, A Sidford
FSTTCS (invited), 2017
292017
Mitigating Covariate Shift in Imitation Learning via Offline Data Without Great Coverage
JD Chang, M Uehara, D Sreenivas, R Kidambi, W Sun
Conference on Neural Information Processing Systems (NeurIPS) 2021, 2021
23*2021
Submodular hamming metrics
J Gillenwater, R Iyer, B Lusch, R Kidambi, J Bilmes
Conference on Neural Information Processing Systems (NeurIPS), 2015
192015
Leverage score sampling for faster accelerated regression and ERM
N Agarwal, S Kakade, R Kidambi, YT Lee, P Netrapalli, A Sidford
Algorithmic Learning Theory (ALT), 2020, 2020
172020
MobILE: Model-Based Imitation Learning From Observation Alone
R Kidambi, J Chang, W Sun
Conference on Neural Information Processing Systems (NeurIPS) 2021, 2021
15*2021
Making Paper Reviewing Robust to Bid Manipulation Attacks
R Wu, C Guo, F Wu, R Kidambi, L van der Maaten, KQ Weinberger
International Conference on Machine Learning (ICML) 2021, 2021
152021
Top- eXtreme Contextual Bandits with Arm Hierarchy
R Sen, A Rakhlin, L Ying, R Kidambi, D Foster, D Hill, I Dhillon
International Conference on Machine Learning (ICML) 2021, 2021
132021
Deformable trellises on factor graphs for robust microtubule tracking in clutter
R Kidambi, MC Shih, K Rose
IEEE International Symposium on Biomedical Imaging (ISBI), 2012, 2012
62012
Open Problem: Do Good Algorithms Necessarily Query Bad Points?
R Ge, P Jain, SM Kakade, R Kidambi, DM Nagaraj, P Netrapalli
Conference on Learning Theory (COLT), 2019, 2019
32019
Efficient estimation of generalization error and bias-variance components of ensembles
D Mahajan, V Gupta, SS Keerthi, S Sundararajan, S Narayanamurthy, ...
arXiv preprint arXiv:1711.05482, 2017
32017
Stochastic Gradient Descent For Modern Machine Learning: Theory, Algorithms And Applications
R Kidambi
University of Washington Seattle, 2019
12019
On shannon capacity and causal estimation
R Kidambi, S Kannan
Annual Allerton Conference on Communication, Control, and Computing …, 2015
12015
Counterfactual Learning To Rank for Utility-Maximizing Query Autocompletion
A Block, R Kidambi, DN Hill, T Joachims, IS Dhillon
arXiv preprint arXiv:2204.10936, 2022
2022
A Quantitative Evaluation Framework for Missing Value Imputation Algorithms
V Nair, R Kidambi, S Sellamanickam, SS Keerthi, J Gehrke, V Narayanan
arXiv preprint arXiv:1311.2276, 2013
2013
A Structured Prediction Approach for Missing Value Imputation
R Kidambi, V Nair, S Sellamanickam, SS Keerthi
arXiv preprint arXiv:1311.2137, 2013
2013
Sustav trenutno ne može provesti ovu radnju. Pokušajte ponovo kasnije.
Članci 1–20