Följ
Dheeraj Baby
Dheeraj Baby
Verifierad e-postadress på ucsb.edu - Startsida
Titel
Citeras av
Citeras av
År
Optimal dynamic regret in exp-concave online learning
D Baby, YX Wang
Conference on Learning Theory, 359-409, 2021
382021
Online forecasting of total-variation-bounded sequences
D Baby, YX Wang
Advances in Neural Information Processing Systems 32, 2019
382019
Optimal dynamic regret in proper online learning with strongly convex losses and beyond
D Baby, YX Wang
International Conference on Artificial Intelligence and Statistics, 1805-1845, 2022
242022
Optimal dynamic regret in LQR control
D Baby, YX Wang
Advances in Neural Information Processing Systems 35, 24879-24892, 2022
122022
Adaptive online estimation of piecewise polynomial trends
D Baby, YX Wang
Advances in Neural Information Processing Systems 33, 20462-20472, 2020
122020
An optimal reduction of tv-denoising to adaptive online learning
D Baby, X Zhao, YX Wang
International Conference on Artificial Intelligence and Statistics, 2899-2907, 2021
92021
Online label shift: Optimal dynamic regret meets practical algorithms
D Baby, S Garg, TC Yen, S Balakrishnan, Z Lipton, YX Wang
Advances in Neural Information Processing Systems 36, 2024
42024
Initial-state and next-state value folding
JR Baumgartner, RL Kanzelman, PK NALLA, RK Gajavelly, D BABY
US Patent US10621297B1, 2020
42020
Second order path variationals in non-stationary online learning
D Baby, YX Wang
International Conference on Artificial Intelligence and Statistics, 9024-9075, 2023
32023
Near optimal heteroscedastic regression with symbiotic learning
A Das, DM Nagaraj, P Netrapalli, D Baby
The Thirty Sixth Annual Conference on Learning Theory, 3696-3757, 2023
22023
Non-stationary contextual pricing with safety constraints
D Baby, J Xu, YX Wang
12023
Online Feature Updates Improve Online (Generalized) Label Shift Adaptation
R Wu, S Datta, Y Su, D Baby, YX Wang, KQ Weinberger
arXiv preprint arXiv:2402.03545, 2024
2024
Dynamic Regret for Strongly Adaptive Methods and Optimality of Online KRR
D Baby, H Hasson, Y Wang
arXiv preprint arXiv:2111.11550, 2021
2021
Revisiting dynamic regret of strongly adaptive methods
D Baby, H Hasson, B Wang
2021
Supplementary Material for: An Optimal Reduction of TV-Denoising to Adaptive Online Learning
D Baby, X Zhao, YX Wang
Systemet kan inte utföra åtgärden just nu. Försök igen senare.
Artiklar 1–15