Travis Dick
Cited by
Cited by
Learning to Branch
MF Balcan, T Dick, T Sandholm, E Vitercik
International Conference on Machine Learning, 2018
Real-time prediction learning for the simultaneous actuation of multiple prosthetic joints
PM Pilarski, TB Dick, RS Sutton
2013 IEEE 13th International Conference on Rehabilitation Robotics (ICORR), 1-8, 2013
Sepo: Selecting by pointing as an intuitive human-robot command interface
CP Quintero, RT Fomena, A Shademan, N Wolleb, T Dick, M Jagersand
2013 IEEE International Conference on Robotics and Automation, 1166-1171, 2013
Online learning in Markov decision processes with changing cost sequences
T Dick, A Gyorgy, C Szepesvari
International Conference on Machine Learning, 512-520, 2014
Realtime Registration-Based Tracking via Approximate Nearest Neighbour Search.
T Dick, CP Quintero, M Jägersand, A Shademan
Robotics: Science and Systems, 2013
Differentially private clustering in high-dimensional euclidean spaces
MF Balcan, T Dick, Y Liang, W Mou, H Zhang
Proceedings of the 34th International Conference on Machine Learning-Volume …, 2017
Dispersion for data-driven algorithm design, online learning, and private optimization
MF Balcan, T Dick, E Vitercik
2018 IEEE 59th Annual Symposium on Foundations of Computer Science (FOCS …, 2018
Envy-free classification
MFF Balcan, T Dick, R Noothigattu, AD Procaccia
Advances in Neural Information Processing Systems, 1238-1248, 2019
Data driven resource allocation for distributed learning
T Dick, M Li, VK Pillutla, C White, MF Balcan, A Smola
Workshops at the Thirty-First AAAI Conference on Artificial Intelligence, 2017
How many random restarts are enough
T Dick, E Wong, C Dann
Technical report, 2014
Data-driven clustering via parameterized lloyd's families
MFF Balcan, T Dick, C White
Advances in Neural Information Processing Systems, 10641-10651, 2018
Private covariance estimation via iterative eigenvector sampling
K Amin, T Dick, A Kulesza, AM Medina, S Vassilvitskii
2018 NIPS workshop in Privacy-Preserving Machine Learning 250, 2018
Policy Gradient Reinforcement Learning Without Regret
TB Dick
Random Smoothing Might be Unable to Certify Robustness for High-Dimensional Images
A Blum, T Dick, N Manoj, H Zhang
arXiv preprint arXiv:2002.03517, 2020
How much data is sufficient to learn high-performing algorithms?
MF Balcan, D DeBlasio, T Dick, C Kingsford, T Sandholm, E Vitercik
arXiv preprint arXiv:1908.02894, 2019
Learning to Link
MF Balcan, T Dick, M Lang
arXiv preprint arXiv:1907.00533, 2019
Semi-bandit Optimization in the Dispersed Setting
MF Balcan, T Dick, W Pegden
arXiv preprint arXiv:1904.09014, 2019
Differentially Private Covariance Estimation
K Amin, T Dick, A Kulesza, A Munoz, S Vassilvitskii
Advances in Neural Information Processing Systems, 14190-14199, 2019
Label efficient learning by exploiting multi-class output codes
MF Balcan, T Dick, Y Mansour
Thirty-First AAAI Conference on Artificial Intelligence, 2017
Lunar Lander: A Continous-Action Case Study for Policy-Gradient Actor-Critic Algorithms
R Shariff, T Dick
RLDM, 2013
The system can't perform the operation now. Try again later.
Articles 1–20