Articles with public access mandates - Alon OrlitskyLearn more
Available somewhere: 20
Optimal prediction of the number of unseen species
A Orlitsky, AT Suresh, Y Wu
Proceedings of the National Academy of Sciences 113 (47), 13283-13288, 2016
Mandates: US National Science Foundation
Maximum selection and ranking under noisy comparisons
M Falahatgar, A Orlitsky, V Pichapati, AT Suresh
International Conference on Machine Learning, 1088-1096, 2017
Mandates: US National Science Foundation
Maxing and ranking with few assumptions
M Falahatgar, Y Hao, A Orlitsky, V Pichapati, V Ravindrakumar
Advances in Neural Information Processing Systems 30, 2017
Mandates: US National Science Foundation
The limits of maxing, ranking, and preference learning
M Falahatgar, A Jain, A Orlitsky, V Pichapati, V Ravindrakumar
International conference on machine learning, 1427-1436, 2018
Mandates: US National Science Foundation
Silence-based communication
AK Dhulipala, C Fragouli, A Orlitsky
IEEE Transactions on Information Theory 56 (1), 350-366, 2009
Mandates: Swiss National Science Foundation
A unified maximum likelihood approach for estimating symmetric properties of discrete distributions
J Acharya, H Das, A Orlitsky, AT Suresh
International Conference on Machine Learning, 11-21, 2017
Mandates: US National Science Foundation
The broad optimality of profile maximum likelihood
Y Hao, A Orlitsky
Advances in Neural Information Processing Systems 32, 2019
Mandates: US National Science Foundation
A general method for robust learning from batches
A Jain, A Orlitsky
Advances in Neural Information Processing Systems 33, 21775-21785, 2020
Mandates: US National Science Foundation
Optimal robust learning of discrete distributions from batches
A Jain, A Orlitsky
International Conference on Machine Learning, 4651-4660, 2020
Mandates: US National Science Foundation
Unified sample-optimal property estimation in near-linear time
Y Hao, A Orlitsky
Advances in Neural Information Processing Systems 32, 2019
Mandates: US National Science Foundation
Data amplification: Instance-optimal property estimation
Y Hao, A Orlitsky
International Conference on Machine Learning, 4049-4059, 2020
Mandates: US National Science Foundation
Maximum selection and sorting with adversarial comparators
J Acharya, M Falahatgar, A Jafarpour, A Orlitsky, AT Suresh
Journal of Machine Learning Research 19 (59), 1-31, 2018
Mandates: US National Science Foundation
Doubly-competitive distribution estimation
Y Hao, A Orlitsky
International Conference on Machine Learning, 2614-2623, 2019
Mandates: US National Science Foundation
Robust density estimation from batches: The best things in life are (nearly) free
A Jain, A Orlitsky
International Conference on Machine Learning, 4698-4708, 2021
Mandates: US National Science Foundation
The power of absolute discounting: all-dimensional distribution estimation
M Falahatgar, MI Ohannessian, A Orlitsky, V Pichapati
Advances in Neural Information Processing Systems 30, 2017
Mandates: US National Science Foundation
Surf: A simple, universal, robust, fast distribution learning algorithm
Y Hao, A Jain, A Orlitsky, V Ravindrakumar
Advances in Neural Information Processing Systems 33, 10881-10890, 2020
Mandates: US National Science Foundation
Near-optimal smoothing of structured conditional probability matrices
M Falahatgar, MI Ohannessian, A Orlitsky
Advances in Neural Information Processing Systems 29, 2016
Mandates: US National Science Foundation
Profile entropy: A fundamental measure for the learnability and compressibility of distributions
Y Hao, A Orlitsky
Advances in Neural Information Processing Systems 33, 6947-6958, 2020
Mandates: US National Science Foundation
Linear-sample learning of low-rank distributions
A Jain, A Orlitsky
Advances in Neural Information Processing Systems 33, 19201-19211, 2020
Mandates: US National Science Foundation
Compressed Maximum Likelihood
Y Hao, A Orlitsky
International Conference on Machine Learning, 4085-4095, 2021
Mandates: US National Science Foundation
Publication and funding information is determined automatically by a computer program