受强制性开放获取政策约束的文章 - Frederic Koehler了解详情
可在其他位置公开访问的文章：26 篇
Information theoretic properties of Markov random fields, and their algorithmic applications
L Hamilton, F Koehler, A Moitra
Advances in Neural Information Processing Systems 30, 2017
强制性开放获取政策： US National Science Foundation
Uniform Convergence of Interpolators: Gaussian Width, Norm Bounds and Benign Overfitting
F Koehler, L Zhou, D Sutherland, N Srebro
Advances in Neural Information Processing Systems 34, 20657-20668, 2021
强制性开放获取政策： US National Science Foundation, US Department of Defense
A spectral condition for spectral gap: fast mixing in high-temperature Ising models
R Eldan, F Koehler, O Zeitouni
Probability theory and related fields 182 (3), 1035-1051, 2022
强制性开放获取政策： US National Science Foundation, US Department of Defense, European Commission
Mean-field approximation, convex hierarchies, and the optimality of correlation rounding: a unified perspective
V Jain, F Koehler, A Risteski
Proceedings of the 51st Annual ACM SIGACT Symposium on Theory of Computing …, 2019
强制性开放获取政策： US National Science Foundation, US Department of Defense
Entropic independence: optimal mixing of down-up random walks
N Anari, V Jain, F Koehler, HT Pham, TD Vuong
Proceedings of the 54th Annual ACM SIGACT Symposium on Theory of Computing …, 2022
强制性开放获取政策： US National Science Foundation, US Department of Defense
Classification Under Misspecification: Halfspaces, Generalized Linear Models, and Connections to Evolvability
S Chen, F Koehler, A Moitra, M Yau
Advances in Neural Information Processing Systems 33, 2020
强制性开放获取政策： US National Science Foundation, US Department of Defense
Online and distribution-free robustness: Regression and contextual bandits with huber contamination
S Chen, F Koehler, A Moitra, M Yau
2021 IEEE 62nd Annual Symposium on Foundations of Computer Science (FOCS …, 2022
强制性开放获取政策： US National Science Foundation, US Department of Defense
Representational aspects of depth and conditioning in normalizing flows
F Koehler, V Mehta, A Risteski
International Conference on Machine Learning, 5628-5636, 2021
强制性开放获取政策： US National Science Foundation, US Department of Defense
Provable algorithms for inference in topic models
S Arora, R Ge, F Koehler, T Ma, A Moitra
International Conference on Machine Learning, 2859-2867, 2016
强制性开放获取政策： US National Science Foundation
The mean-field approximation: Information inequalities, algorithms, and complexity
V Jain, F Koehler, E Mossel
Conference On Learning Theory, 1326-1347, 2018
强制性开放获取政策： US National Science Foundation, US Department of Defense
Learning restricted Boltzmann machines via influence maximization
G Bresler, F Koehler, A Moitra
Proceedings of the 51st Annual ACM SIGACT Symposium on Theory of Computing …, 2019
强制性开放获取政策： US National Science Foundation, US Department of Defense
Learning some popular gaussian graphical models without condition number bounds
J Kelner, F Koehler, R Meka, A Moitra
Advances in Neural Information Processing Systems 33, 10986-10998, 2020
强制性开放获取政策： US National Science Foundation, US Department of Defense
The comparative power of relu networks and polynomial kernels in the presence of sparse latent structure
F Koehler, A Risteski
International Conference on Learning Representations, 2019
强制性开放获取政策： US National Science Foundation
A non-asymptotic moreau envelope theory for high-dimensional generalized linear models
L Zhou, F Koehler, P Sur, DJ Sutherland, N Srebro
Advances in Neural Information Processing Systems 35, 21286-21299, 2022
强制性开放获取政策： US National Science Foundation
Sampling approximately low-rank Ising models: MCMC meets variational methods
F Koehler, H Lee, A Risteski
Conference on Learning Theory, 4945-4988, 2022
强制性开放获取政策： US National Science Foundation
Universality of spectral independence with applications to fast mixing in spin glasses
N Anari, V Jain, F Koehler, HT Pham, TD Vuong
Proceedings of the 2024 Annual ACM-SIAM Symposium on Discrete Algorithms …, 2024
强制性开放获取政策： US National Science Foundation
Multidimensional scaling: Approximation and complexity
E Demaine, A Hesterberg, F Koehler, J Lynch, J Urschel
International conference on machine learning, 2568-2578, 2021
强制性开放获取政策： US National Science Foundation, US Department of Defense
How many subpopulations is too many? Exponential lower bounds for inferring population histories
Y Kim, F Koehler, A Moitra, E Mossel, G Ramnarayan
Research in Computational Molecular Biology: 23rd Annual International …, 2019
强制性开放获取政策： US National Science Foundation, US Department of Defense
Chow-liu++: Optimal prediction-centric learning of tree ising models
E Boix-Adsera, G Bresler, F Koehler
2021 IEEE 62nd Annual Symposium on Foundations of Computer Science (FOCS …, 2022
强制性开放获取政策： US National Science Foundation, US Department of Defense
Reconstruction on trees and low-degree polynomials
F Koehler, E Mossel
Advances in Neural Information Processing Systems 35, 18942-18954, 2022
强制性开放获取政策： US National Science Foundation, US Department of Defense
出版信息和资助信息由计算机程序自动确定