Christopher Liaw
Christopher Liaw
Research Scientist, Google
Verified email at - Homepage
Cited by
Cited by
Nearly-tight VC-dimension and pseudodimension bounds for piecewise linear neural networks
PL Bartlett, N Harvey, C Liaw, A Mehrabian
Journal of Machine Learning Research 20 (63), 1-17, 2019
Tight analyses for non-smooth stochastic gradient descent
NJA Harvey, C Liaw, Y Plan, S Randhawa
Conference on Learning Theory, 1579-1613, 2019
Nearly tight sample complexity bounds for learning mixtures of gaussians via sample compression schemes
H Ashtiani, S Ben-David, N Harvey, C Liaw, A Mehrabian, Y Plan
Advances in Neural Information Processing Systems 31, 2018
A simple tool for bounding the deviation of random matrices on geometric sets
C Liaw, A Mehrabian, Y Plan, R Vershynin
Geometric Aspects of Functional Analysis: Israel Seminar (GAFA) 2014–2016 …, 2017
A new dog learns old tricks: Rl finds classic optimization algorithms
W Kong, C Liaw, A Mehta, D Sivakumar
International conference on learning representations, 2018
Private and polynomial time algorithms for learning Gaussians and beyond
H Ashtiani, C Liaw
Conference on Learning Theory, 1075-1076, 2022
Greedy and local ratio algorithms in the mapreduce model
NJA Harvey, C Liaw, P Liu
Proceedings of the 30th on Symposium on Parallelism in Algorithms and …, 2018
Simple and optimal high-probability bounds for strongly-convex stochastic gradient descent
NJA Harvey, C Liaw, S Randhawa
arXiv preprint arXiv:1909.00843, 2019
Convergence analysis of no-regret bidding algorithms in repeated auctions
Z Feng, G Guruganesh, C Liaw, A Mehta, A Sethi
Proceedings of the AAAI Conference on Artificial Intelligence 35 (6), 5399-5406, 2021
Privately learning mixtures of axis-aligned gaussians
I Aden-Ali, H Ashtiani, C Liaw
Advances in Neural Information Processing Systems 34, 3925-3938, 2021
The value of information concealment
H Fu, C Liaw, P Lu, ZG Tang
Proceedings of the Twenty-Ninth Annual ACM-SIAM Symposium on Discrete …, 2018
Polynomial time and private learning of unbounded gaussian mixture models
J Arbas, H Ashtiani, C Liaw
International Conference on Machine Learning, 1018-1040, 2023
Optimal anytime regret with two experts
NJA Harvey, C Liaw, E Perkins, S Randhawa
Mathematical Statistics and Learning 6 (1), 87-142, 2023
Efficiency of non-truthful auctions under auto-bidding
C Liaw, A Mehta, A Perlroth
arXiv preprint arXiv:2207.03630, 2022
Improved algorithms for online submodular maximization via first-order regret bounds
N Harvey, C Liaw, T Soma
Advances in Neural Information Processing Systems 33, 123-133, 2020
Nearlytight vc-dimension bounds for piecewise linear neural networks
PL Bartlett, N Harvey, C Liaw, A Mehrabian
Proceedings of the 22nd Annual Conference on Learning Theory (COLT 2017) 184 …, 2017
The Vickrey auction with a single duplicate bidder approximates the optimal revenue
H Fu, C Liaw, S Randhawa
Proceedings of the 2019 ACM Conference on Economics and Computation, 419-420, 2019
Mixtures of gaussians are privately learnable with a polynomial number of samples
M Afzali, H Ashtiani, C Liaw
arXiv preprint arXiv:2309.03847, 2023
Efficiency of non-truthful auctions in auto-bidding: The power of randomization
C Liaw, A Mehta, A Perlroth
Proceedings of the ACM Web Conference 2023, 3561-3571, 2023
Approximation schemes for covering and packing in the streaming model
C Liaw, P Liu, R Reiss
arXiv preprint arXiv:1706.09533, 2017
The system can't perform the operation now. Try again later.
Articles 1–20