Theo dõi
Udaya Ghai
Udaya Ghai
Amazon, NYC
Email được xác minh tại amazon.com - Trang chủ
Tiêu đề
Trích dẫn bởi
Trích dẫn bởi
Năm
Exponentiated gradient meets gradient descent
U Ghai, E Hazan, Y Singer
Algorithmic Learning Theory 117, 386-407, 2020
612020
No-regret prediction in marginally stable systems
U Ghai, H Lee, K Singh, C Zhang, Y Zhang
Conference on Learning Theory, 1714-1757, 2020
30*2020
Machine learning for mechanical ventilation control
D Suo, N Agarwal, W Xia, X Chen, U Ghai, A Yu, P Gradu, K Singh, ...
arXiv preprint arXiv:2102.06779, 2021
20*2021
Non-convex online learning via algorithmic equivalence
U Ghai, Z Lu, E Hazan
Advances in Neural Information Processing Systems 35, 22161--22172, 2022
162022
Deluca–A Differentiable Control Library: Environments, Methods, and Benchmarking
P Gradu, J Hallman, D Suo, A Yu, N Agarwal, U Ghai, K Singh, C Zhang, ...
162020
Generating adversarial disturbances for controller verification
U Ghai, D Snyder, A Majumdar, E Hazan
Learning for Dynamics and Control, 1192-1204, 2021
122021
Online nonstochastic model-free reinforcement learning
U Ghai, A Gupta, W Xia, K Singh, E Hazan
Advances in Neural Information Processing Systems 36, 23362-23388, 2023
112023
Robust online control with model misspecification
U Ghai, X Chen, E Hazan, A Megretski
Learning for Dynamics and Control Conference, 1163-1175, 2022
7*2022
A Regret Minimization Approach to Multi-Agent Control
U Ghai, U Madhushani, N Leonard, E Hazan
International Conference on Machine Learning 162, 7422--7434, 2022
62022
How Does Critical Batch Size Scale in Pre-training?
H Zhang, D Morwani, N Vyas, J Wu, D Zou, U Ghai, D Foster, S Kakade
arXiv preprint arXiv:2410.21676, 2024
32024
Sample-Efficient Agnostic Boosting
U Ghai, K Singh
arXiv preprint arXiv:2410.23632, 2024
12024
Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models
Y Song, H Zhang, C Eisenach, SM Kakade, D Foster, U Ghai
NeurIPS 2024 Workshop on Mathematics of Modern Machine Learning, 2024
12024
Sample-Optimal Agnostic Boosting with Unlabeled Data
U Ghai, K Singh
arXiv preprint arXiv:2503.04706, 2025
2025
A shared-revenue Bertrand game
R Pabari, U Ghai, D Perrault-Joncas, K Torkkola, O Ronen, D Madeka, ...
arXiv preprint arXiv:2502.07952, 2025
2025
Neural Coordination and Capacity Control for Inventory Management
C Eisenach, U Ghai, D Madeka, K Torkkola, D Foster, S Kakade
arXiv preprint arXiv:2410.02817, 2024
2024
A Game-Theoretic Lens for Robustness in Control
U Ghai
Princeton University, 2024
2024
Hệ thống không thể thực hiện thao tác ngay bây giờ. Hãy thử lại sau.
Bài viết 1–16