Следене
Ramki Gummadi
Ramki Gummadi
Google
Потвърден имейл адрес: google.com
Заглавие
Позовавания
Позовавания
Година
Optimal bidding strategies in dynamic auctions with budget constraints
R Gummadi, PB Key, A Proutiere
2011 49th Annual Allerton Conference on Communication, Control, and …, 2011
94*2011
Relaying a fountain code across multiple nodes
R Gummadi, RS Sreenivas
2008 IEEE Information Theory Workshop, 149-153, 2008
662008
Variational rejection sampling
A Grover, R Gummadi, M Lazaro-Gredilla, D Schuurmans, S Ermon
International Conference on Artificial Intelligence and Statistics, 823-832, 2018
412018
Analysis of medicare pay-for-performance contracts
H Bastani, M Bayati, M Braverman, R Gummadi, R Johari
EC 2017 Workshop on Mechanism Design for Social Good, 2017
402017
Mean field equilibria of multi armed bandit games
R Gummadi, R Johari, JY Yu
2012 50th Annual Allerton Conference on Communication, Control, and …, 2012
40*2012
Surrogate objectives for batch policy optimization in one-step decision making
M Chen, R Gummadi, C Harris, D Schuurmans
NeurIPS 2019, 2019
322019
{HALP}: Heuristic aided learned preference eviction policy for {YouTube} content delivery network
Z Song, K Chen, Ν Sarda, D Altınbüken, E Brevdo, J Coleman, X Ju, ...
20th USENIX Symposium on Networked Systems Design and Implementation (NSDI …, 2023
252023
Characterizing the Gap Between Actor-Critic and Policy Gradient
J Wen, S Kumar, R Gummadi, D Schuurmans
ICML 2021, 2021
192021
Understanding and leveraging overparameterization in recursive value estimation
C Xiao, B Dai, J Mei, OA Ramirez, R Gummadi, C Harris, D Schuurmans
International Conference on Learning Representations, 2021
172021
Computing the capacity region of a wireless network
R Gummadi, K Jung, D Shah, R Sreenivas
IEEE INFOCOM 2009, 1341-1349, 2009
172009
Feasible rate allocation in wireless networks
R Gummadi, K Jung, D Shah, R Sreenivas
IEEE INFOCOM 2008-The 27th Conference on Computer Communications, 995-1003, 2008
112008
Coding and scheduling in networks for erasures and broadcast
SR Gummadi
UIUC, 2011
82011
Target networks and over-parameterization stabilize off-policy bootstrapping with function approximation
F Che, C Xiao, J Mei, B Dai, R Gummadi, OA Ramirez, CK Harris, ...
arXiv preprint arXiv:2405.21043, 2024
52024
On tractable instances of modular supervisory control
R Gummadi, N Singh, RS Sreenivas
IEEE transactions on automatic control 56 (7), 1621-1635, 2010
52010
The role of feedback in the choice between routing and coding for wireless unicast
R Gummadi, L Massoulie, R Sreenivas
2010 IEEE International Symposium on Network Coding (NetCod), 1-6, 2010
52010
Broadcasting with side information
R Gummadi, A Shokrollahi, R Sreenivas
2010 IEEE Information Theory Workshop on Information Theory (ITW 2010, Cairo …, 2010
52010
Key, and Alexandre Proutière. 2011. Optimal bidding strategies in dynamic auctions with budget constraints
R Gummadi, B Peter
Allerton. IEEE 588, 0
5
Feasible -Learning for Average Reward Reinforcement Learning
Y Jin, R Gummadi, Z Zhou, J Blanchet
International Conference on Artificial Intelligence and Statistics, 1630-1638, 2024
42024
Optimal control of a broadcasting server
R Gummadi
Proceedings of the 48h IEEE Conference on Decision and Control (CDC) held …, 2009
42009
Satisficing exploration for deep reinforcement learning
D Arumugam, S Kumar, R Gummadi, B Van Roy
arXiv preprint arXiv:2407.12185, 2024
32024
Системата не може да изпълни операцията сега. Опитайте отново по-късно.
Статии 1–20