Følg
Dhruv Madeka
Dhruv Madeka
Principal Machine Learning Scientist, Amazon
Verificeret mail på bu.edu - Startside
Titel
Citeret af
Citeret af
År
A multi-horizon quantile recurrent forecaster
R Wen, K Torkkola, B Narayanaswamy, D Madeka
arXiv preprint arXiv:1711.11053, 2017
4422017
Scatteract: Automated extraction of data from scatter plots
M Cliche, D Rosenberg, D Madeka, C Yee
Machine Learning and Knowledge Discovery in Databases: European Conference …, 2017
772017
Mqtransformer: Multi-horizon forecasts with context dependent and feedback-aware attention
C Eisenach, Y Patel, D Madeka
arXiv preprint arXiv:2009.14799, 2020
292020
Deep Inventory Management
D Madeka, K Torkkola, C Eisenach, D Foster, A Luo, SM Kakade
arXiv preprint arXiv:2210.03137, 2022
182022
Sample path generation for probabilistic demand forecasting
D Madeka, L Swiniarski, D Foster, L Razoumov, K Torkkola, R Wen
92018
All roads lead to quantitative finance
NN Taleb, D Madeka
Quantitative Finance 19 (11), 1775-1776, 2019
62019
MQRetNN: Multi-horizon time series forecasting with retrieval augmentation
S Yang, C Eisenach, D Madeka
arXiv preprint arXiv:2207.10517, 2022
52022
Accurate prediction of electoral outcomes
D Madeka
arXiv preprint arXiv:1704.02664, 2017
52017
A Framework for the Meta-Analysis of Randomized Experiments with Applications to Heavy-Tailed Response Data
N Tripuraneni, D Madeka, D Foster, D Perrault-Joncas, MI Jordan
arXiv preprint arXiv:2112.07602, 2021
4*2021
A Study on the Calibration of In-context Learning
H Zhang, YF Zhang, Y Yu, D Madeka, D Foster, E Xing, H Lakkaraju, ...
arXiv preprint arXiv:2312.04021, 2023
32023
Scaling laws for imitation learning in nethack
J Tuyls, D Madeka, K Torkkola, D Foster, K Narasimhan, S Kakade
arXiv preprint arXiv:2307.09423, 2023
32023
A few expert queries suffices for sample-efficient rl with resets and linear value approximation
P Amortila, N Jiang, D Madeka, DP Foster
Advances in Neural Information Processing Systems 35, 29637-29648, 2022
22022
Learning an Inventory Control Policy with General Inventory Arrival Dynamics
S Andaz, C Eisenach, D Madeka, K Torkkola, R Jia, D Foster, S Kakade
arXiv preprint arXiv:2310.17168, 2023
12023
Linear reinforcement learning with ball structure action space
Z Jia, R Jia, D Madeka, DP Foster
International Conference on Algorithmic Learning Theory, 755-775, 2023
12023
Contextual Bandits for Evaluating and Improving Inventory Control Policies
D Foster, R Jia, D Madeka
arXiv preprint arXiv:2310.16096, 2023
2023
Scaling Laws for Imitation Learning in Single-Agent Games
J Tuyls, D Madeka, K Torkkola, D Foster, KR Narasimhan, SM Kakade
2023
Distribution-free multi-horizon forecasting and vending system
V Quenneville-Belair, M Wolff, B Willhelme, D Madeka, D Foster
2023
Estimating Covariance Matrices for Investments Whose Histories Differ in Length
D Madeka, W Nilsen
Available at SSRN 2331085, 2013
2013
Systemet kan ikke foretage handlingen nu. Prøv igen senere.
Artikler 1–18