More Like this

1. Ten Steps of EM Suffice for Mixtures of Two Gaussians

   Daskalakis, Constantinos; Tzamos, Christos; Zampetakis, Manolis (January 2017, 30th Annual Conference on Learning Theory)

   The Expectation-Maximization (EM) algorithm is a widely used method for maximum likelihood estimation in models with latent variables. For estimating mixtures of Gaussians, its iteration can be viewed as a soft version of the k-means clustering algorithm. Despite its wide use and applications, there are essentially no known convergence guarantees for this method. We provide global convergence guarantees for mixtures of two Gaussians with known covariance matrices. We show that the population version of EM, where the algorithm is given access to infinitely many samples from the mixture, converges geometrically to the correct mean vectors, and provide simple, closed-form expressions for the convergence rate. As a simple illustration, we show that, in one dimension, ten steps of the EM algorithm initialized at infinity result in less than 1\% error estimation of the means. In the finite sample regime, we show that, under a random initialization, Õ (d/ϵ2) samples suffice to compute the unknown vectors to within ϵ in Mahalanobis distance, where d is the dimension. In particular, the error rate of the EM based estimator is Õ (dn‾‾√) where n is the number of samples, which is optimal up to logarithmic factors. 

   more » « less
2. Sharp analysis of EM for learning mixtures of pairwise differences

   Dhawan, Abhishek; Mao, Cheng; Pananjady, Ashwin (July 2023, Proceedings of Thirty Sixth Conference on Learning Theory)

   We consider a symmetric mixture of linear regressions with random samples from the pairwise comparison design, which can be seen as a noisy version of a type of Euclidean distance geometry problem. We analyze the expectation-maximization (EM) algorithm locally around the ground truth and establish that the sequence converges linearly, providing an $$\ell_\infty$$-norm guarantee on the estimation error of the iterates. Furthermore, we show that the limit of the EM sequence achieves the sharp rate of estimation in the $$\ell_2$$-norm, matching the information-theoretically optimal constant. We also argue through simulation that convergence from a random initialization is much more delicate in this setting, and does not appear to occur in general. Our results show that the EM algorithm can exhibit several unique behaviors when the covariate distribution is suitably structured. 

   more » « less
3. The EM Algorithm gives Sample Optimality for Learning Mixtures of Well-Separated Gaussians

   Kwon, Jeongyeol; Caramanis, Constantine (July 2020, Proceedings of Thirty Third Conference on Learning Theory)

   We consider the problem of spherical Gaussian Mixture models with 𝑘≥3 components when the components are well separated. A fundamental previous result established that separation of Ω(log𝑘‾‾‾‾‾√) is necessary and sufficient for identifiability of the parameters with \textit{polynomial} sample complexity (Regev and Vijayaraghavan, 2017). In the same context, we show that 𝑂̃ (𝑘𝑑/𝜖2) samples suffice for any 𝜖≲1/𝑘, closing the gap from polynomial to linear, and thus giving the first optimal sample upper bound for the parameter estimation of well-separated Gaussian mixtures. We accomplish this by proving a new result for the Expectation-Maximization (EM) algorithm: we show that EM converges locally, under separation Ω(log𝑘‾‾‾‾‾√). The previous best-known guarantee required Ω(𝑘‾‾√) separation (Yan, et al., 2017). Unlike prior work, our results do not assume or use prior knowledge of the (potentially different) mixing weights or variances of the Gaussian components. Furthermore, our results show that the finite-sample error of EM does not depend on non-universal quantities such as pairwise distances between means of Gaussian components. 

   more » « less
4. Alternating minimization for generalized rank-1 matrix sensing: sharp predictions from a random initialization

   https://doi.org/10.1093/imaiai/iaae025  

   Chandrasekher, Kabir_Aladin; Lou, Mengqi; Pananjady, Ashwin (September 2024, Information and Inference: A Journal of the IMA)

   Abstract We consider the problem of estimating the factors of a rank-$$1$$ matrix with i.i.d. Gaussian, rank-$$1$$ measurements that are nonlinearly transformed and corrupted by noise. Considering two prototypical choices for the nonlinearity, we study the convergence properties of a natural alternating update rule for this non-convex optimization problem starting from a random initialization. We show sharp convergence guarantees for a sample-split version of the algorithm by deriving a deterministic one-step recursion that is accurate even in high-dimensional problems. Notably, while the infinite-sample population update is uninformative and suggests exact recovery in a single step, the algorithm—and our deterministic one-step prediction—converges geometrically fast from a random initialization. Our sharp, non-asymptotic analysis also exposes several other fine-grained properties of this problem, including how the nonlinearity and noise level affect convergence behaviour. On a technical level, our results are enabled by showing that the empirical error recursion can be predicted by our deterministic one-step updates within fluctuations of the order $$n^{-1/2}$$ when each iteration is run with $$n$$ observations. Our technique leverages leave-one-out tools originating in the literature on high-dimensional $$M$$-estimation and provides an avenue for sharply analyzing complex iterative algorithms from a random initialization in other high-dimensional optimization problems with random data. 

   more » « less
5. Toward Global Convergence of Gradient EM for Over-Parameterized Gaussian Mixture Models

   Xu, Weihang; Fazel, Maryam; Du, Simon S (September 2024, Advances in Neural Information Processing Systems)

   We study the gradient Expectation-Maximization (EM) algorithm for Gaussian Mixture Models (GMM) in the over-parameterized setting, where a general GMM with n > 1 components learns from data that are generated by a single ground truth Gaussian distribution. While results for the special case of 2-Gaussian mixtures are well-known, a general global convergence analysis for arbitrary n remains unresolved and faces several new technical barriers since the convergence becomes sub-linear and non-monotonic. To address these challenges, we construct a novel likelihood-based convergence analysis framework and rigorously prove that gradient EM converges globally with a sublinear rate O(1/\sqrt{t}). This is the first global convergence result for Gaussian mixtures with more than 2 components. The sublinear convergence rate is due to the algorithmic nature of learning over- parameterized GMM with gradient EM. We also identify a new emerging technical challenge for learning general over-parameterized GMM: the existence of bad local regions that can trap gradient EM for an exponential number of steps. 

   more » « less