Corpus ID: 6820421

The More, the Merrier: the Blessing of Dimensionality for Learning Large Gaussian Mixtures

@article{Anderson2014TheMT,
  title={The More, the Merrier: the Blessing of Dimensionality for Learning Large Gaussian Mixtures},
  author={J. Anderson and Mikhail Belkin and Navin Goyal and Luis Rademacher and James R. Voss},
  journal={ArXiv},
  year={2014},
  volume={abs/1311.2891}
}
In this paper we show that very large mixtures of Gaussians are efficiently learnable in high dimension. More precisely, we prove that a mixture with known identical covariance matrices whose number of components is a polynomial of any fixed degree in the dimension n is polynomially learnable as long as a certain non-degeneracy condition on the means is satisfied. It turns out that this condition is generic in the sense of smoothed complexity, as soon as the dimensionality of the space is high… Expand
73 Citations
Learning Mixtures of Gaussians in High Dimensions
  • 86
  • Highly Influenced
  • PDF
On Learning Mixtures of Well-Separated Gaussians
  • 38
  • Highly Influenced
  • PDF
Robust and Proper Learning for Mixtures of Gaussians via Systems of Polynomial Inequalities
  • 21
  • Highly Influenced
  • PDF
Provable Learning of Overcomplete Latent Variable Models: Semi-supervised and Unsupervised Settings
  • 6
  • PDF
Mixture models, robustness, and sum of squares proofs
  • 85
  • PDF
Clustering Semi-Random Mixtures of Gaussians
  • 6
  • PDF
Out-of-Sample Error Estimation: The Blessing of High Dimensionality
  • 3
Statistical Query Lower Bounds for Robust Estimation of High-Dimensional Gaussians and Gaussian Mixtures
  • 115
  • PDF
Principled approaches to robust machine learning and beyond
  • J. Li
  • Computer Science
  • 2018
  • 25
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 43 REFERENCES
Settling the Polynomial Learnability of Mixtures of Gaussians
  • Ankur Moitra, G. Valiant
  • Computer Science, Mathematics
  • 2010 IEEE 51st Annual Symposium on Foundations of Computer Science
  • 2010
  • 268
  • Highly Influential
  • PDF
Polynomial Learning of Distribution Families
  • Mikhail Belkin, K. Sinha
  • Computer Science, Mathematics
  • 2010 IEEE 51st Annual Symposium on Foundations of Computer Science
  • 2010
  • 182
  • PDF
Learning mixtures of arbitrary gaussians
  • 237
Estimating the Unseen: Improved Estimators for Entropy and other Properties
  • 48
Smoothed analysis of tensor decompositions
  • 109
  • PDF
A spectral algorithm for learning mixtures of distributions
  • S. Vempala, Grant Wang
  • Mathematics, Computer Science
  • The 43rd Annual IEEE Symposium on Foundations of Computer Science, 2002. Proceedings.
  • 2002
  • 149
Noise stability of functions with low influences: Invariance and optimality
  • 318
  • PDF
Blind Signal Separation in the Presence of Gaussian Noise
  • 20
  • PDF
...
1
2
3
4
5
...