Learning a Gaussian mixture model (GMM) is a fundamental problem in machine learning, learning theory, and statistics. One notion of learning a GMM is proper learning: here, the goal is to find a mixture of $k$ Gaussians $\mathcal{M}$ that is close to the density $f$ of the unknown distribution from which we draw samples. The distance between $\mathcal{M}$ and $f$ is typically measured in the total variation or $L_1$-norm.
We give an algorithm for learning a mixture of $k$ univariate Gaussians that is nearly optimal for any fixed $k$. The sample complexity of our algorithm is $\tilde{O}(\frac{k}{ε^2})$ and the running time is $(k \cdot \log\frac{1}ε)^{O(k^4)} + \tilde{O}(\frac{k}{ε^2})$. It is well-known that this sample complexity is optimal (up to logarithmic factors), and it was already achieved by prior work. However, the best known time complexity for proper learning a $k$-GMM was $\tilde{O}(\frac{1}{ε^{3k-1}})$. In particular, the dependence between $\frac{1}ε$ and $k$ was exponential. We significantly improve this dependence by replacing the $\frac{1}ε$ term with a $\log \frac{1}ε$ while only increasing the exponent moderately. Hence, for any fixed $k$, the $\tilde{O} (\frac{k}{ε^2})$ term dominates our running time, and thus our algorithm runs in time which is nearly-linear in the number of samples drawn. Achieving a running time of $\textrm{poly}(k, \frac{1}ε)$ for proper learning of $k$-GMMs has recently been stated as an open problem by multiple researchers, and we make progress on this question.
Moreover, our approach offers an agnostic learning guarantee: our algorithm returns a good GMM even if the distribution we are sampling from is not a mixture of Gaussians. To the best of our knowledge, our algorithm is the first agnostic proper learning algorithm for GMMs.
Continuously learning to solve unseen tasks with limited experience has been extensively pursued in meta-learning and continual learning, but with restricted assumptions such as accessible task distributions, independently and identically distributed tasks, and clear task delineations. However, real-world physical tasks frequently violate these assumptions, resulting in performance degradation. This paper proposes a continual online model-based reinforcement learning approach that does not require pre-training to solve task-agnostic problems with unknown task boundaries. We maintain a mixture …
University of Waterloo（滑铁卢大学）；Simons Institute for Theory of Computing（西蒙斯理论计算研究所）；University of California, Berkeley（加州大学伯克利分校）
We consider PAC learning of probability distributions (a.k.a. density estimation), where we are given an i.i.d. sample generated from an unknown target distribution, and want to output a distribution that is close to the target in total variation distance. Let $\mathcal F$ be an arbitrary class of probability distributions, and let $\mathcal{F}^k$ denote the class of $k$-mixtures of elements of $\mathcal F$. Assuming the existence of a method for learning $\mathcal F$ with sample complexity $m_{\mathcal{F}}(ε)$, we provide a method for learning $\mathcal F^k$ with sample complexity $O({k\log k…
We study location-scale mixture priors for nonparametric statistical problems, including multivariate regression, density estimation and classification. We show that a rate-adaptive procedure can be obtained if the prior is properly constructed. In particular, we show that adaptation is achieved if a kernel mixture prior on a regression function is constructed using a Gaussian kernel, an inverse gamma bandwidth, and Gaussian mixing weights.
The computation of two Bayesian predictive distributions which are discrete mixtures of incomplete beta functions is considered. The number of iterations can easily become large for these distributions and thus, the accuracy of the result can be questionable. Therefore, existing algorithms for that class of mixtures are improved by introducing round-off error calculation into the stopping rule. A further simple modification is proposed to deal with possible underflows that may prevent recurrence to work properly.
We provide an algorithm for properly learning mixtures of two single-dimensional Gaussians without any separability assumptions. Given $\tilde{O}(1/\varepsilon^2)$ samples from an unknown mixture, our algorithm outputs a mixture that is $\varepsilon$-close in total variation distance, in time $\tilde{O}(1/\varepsilon^5)$. Our sample complexity is optimal up to logarithmic factors, and significantly improves upon both Kalai et al., whose algorithm has a prohibitive dependence on $1/\varepsilon$, and Feldman et al., whose algorithm requires bounds on the mixture parameters and depends pseudo-pol…
When constructing a Bayesian Machine Learning model, we might be faced with multiple different prior distributions and thus are required to properly consider them in a sensible manner in our model. While this situation is reasonably well explored for classical Bayesian Statistics, it appears useful to develop a corresponding method for complex Machine Learning problems. Given their underlying Bayesian framework and their widespread popularity, Gaussian Processes are a good candidate to tackle this task. We therefore extend the idea of Mixture models for Gaussian Process regression in order to …
McMaster University（麦克马斯特大学）；Vector Institute（向量研究所）；University of Waterloo（滑铁卢大学）；University of British Columbia（不列颠哥伦比亚大学）；McGill University（麦吉尔大学）
We prove that $\tildeΘ(k d^2 / \varepsilon^2)$ samples are necessary and sufficient for learning a mixture of $k$ Gaussians in $\mathbb{R}^d$, up to error $\varepsilon$ in total variation distance. This improves both the known upper bounds and lower bounds for this problem. For mixtures of axis-aligned Gaussians, we show that $\tilde{O}(k d / \varepsilon^2)$ samples suffice, matching a known lower bound. Moreover, these results hold in the agnostic-learning/robust-estimation setting as well, where the target distribution is only approximately a mixture of Gaussians. The upper bound is shown us…
We study the supervised clustering problem under the two-component anisotropic Gaussian mixture model in high dimensions and in the non-asymptotic setting. We first derive a lower and a matching upper bound for the minimax risk of clustering in this framework. We also show that in the high-dimensional regime, the linear discriminant analysis (LDA) classifier turns out to be sub-optimal in the minimax sense. Next, we characterize precisely the risk of $\ell_2$-regularized supervised least squares classifiers. We deduce the fact that the interpolating solution may outperform the regularized clas…
Ulm University（乌尔姆大学）；Institute of Neural Information Processing（神经信息处理研究所）
One weakness of machine learning algorithms is the poor ability of models to solve new problems without forgetting previously acquired knowledge. The Continual Learning (CL) paradigm has emerged as a protocol to systematically investigate settings where the model sequentially observes samples generated by a series of tasks. In this work, we take a task-agnostic view of continual learning and develop a hierarchical information-theoretic optimality principle that facilitates a trade-off between learning and forgetting. We discuss this principle from a Bayesian perspective and show its connection…
One notable weakness of current machine learning algorithms is the poor ability of models to solve new problems without forgetting previously acquired knowledge. The Continual Learning paradigm has emerged as a protocol to systematically investigate settings where the model sequentially observes samples generated by a series of tasks. In this work, we take a task-agnostic view of continual learning and develop a hierarchical information-theoretic optimality principle that facilitates a trade-off between learning and forgetting. We derive this principle from a Bayesian perspective and show its …
UC Berkeley（加州大学伯克利分校）；University of Edinburgh（爱丁堡大学）；Columbia University（哥伦比亚大学）
We give a highly efficient "semi-agnostic" algorithm for learning univariate probability distributions that are well approximated by piecewise polynomial density functions. Let $p$ be an arbitrary distribution over an interval $I$ which is $τ$-close (in total variation distance) to an unknown probability distribution $q$ that is defined by an unknown partition of $I$ into $t$ intervals and $t$ unknown degree-$d$ polynomials specifying $q$ over each of the intervals. We give an algorithm that draws $\tilde{O}(t\new{(d+1)}/\eps^2)$ samples from $p$, runs in time $\poly(t,d,1/\eps)$, and with hig…
Ecologists often interpret variation in the spatial distribution of populations in terms of responses to environmental features, but disentangling the effects of individual variables can be difficult if latent effects and spatial and temporal correlations are not accounted for properly. Here, we use hierarchical models based on a Poisson log-normal mixture to understand the spatial variation in relative abundance (counts per standardized unit of effort) of yellow perch, Perca flavescens, the most abundant fish species in Lake Saint Pierre, Quebec, Canada. The mixture incorporates spatially var…
Uncertainty-Aware Strategies: A Model-Agnostic Framework for Robust Financial Optimization through Subsampling
Department of Mathematics TU Munich（数学系慕尼黑工业大学）；Mathematical Institute/ Oxford Man Institute University of Oxford（数学研究所/牛津曼研究所牛津大学）；Department of Mathematical Stochastics University of Freiburg（数学随机系弗赖堡大学）
In longitudinal studies, subjects may be lost to follow-up, or miss some of the planned visits, leading to incomplete response sequences. When the probability of non-response, conditional on the available covariates and the observed responses, still depends on unobserved outcomes, the dropout mechanism is said to be non ignorable. A common objective is to build a reliable association structure to account for dependence between the longitudinal and the dropout processes. Starting from the existing literature, we introduce a random coefficient based dropout model where the association between ou…
The Ohio State University（俄亥俄州立大学）；Princeton University（普林斯顿大学）
We initiate the study of a new model of supervised learning under privacy constraints. Imagine a medical study where a dataset is sampled from a population of both healthy and unhealthy individuals. Suppose healthy individuals have no privacy concerns (in such case, we call their data "public") while the unhealthy individuals desire stringent privacy protection for their data. In this example, the population (data distribution) is a mixture of private (unhealthy) and public (healthy) sub-populations that could be very different. Inspired by the above example, we consider a model in which the p…
We consider the problem of estimating the mean and covariance of a distribution from iid samples in $\mathbb{R}^n$, in the presence of an $η$ fraction of malicious noise; this is in contrast to much recent work where the noise itself is assumed to be from a distribution of known type. The agnostic problem includes many interesting special cases, e.g., learning the parameters of a single Gaussian (or finding the best-fit Gaussian) when $η$ fraction of data is adversarially corrupted, agnostically learning a mixture of Gaussians, agnostic ICA, etc. We present polynomial-time algorithms to estima…
We give an $n^{O(\log\log n)}$-time membership query algorithm for properly and agnostically learning decision trees under the uniform distribution over $\{\pm 1\}^n$. Even in the realizable setting, the previous fastest runtime was $n^{O(\log n)}$, a consequence of a classic algorithm of Ehrenfeucht and Haussler. Our algorithm shares similarities with practical heuristics for learning decision trees, which we augment with additional ideas to circumvent known lower bounds against these heuristics. To analyze our algorithm, we prove a new structural result for decision trees that strengthens a …
University of Wisconsin, Madison（威斯康星大学麦迪逊分校）；University of California, San Diego（加利福尼亚大学圣地亚哥分校）；University of California, Berkeley（加利福尼亚大学伯克利分校）；Google Research（谷歌研究院）
We study the problem of {\em properly} learning large margin halfspaces in the agnostic PAC model. In more detail, we study the complexity of properly learning $d$-dimensional halfspaces on the unit ball within misclassification error $α\cdot \mathrm{OPT}_γ + ε$, where $\mathrm{OPT}_γ$ is the optimal $γ$-margin error rate and $α\geq 1$ is the approximation ratio. We give learning algorithms and computational hardness results for this problem, for all values of the approximation ratio $α\geq 1$, that are nearly-matching for a range of parameters. Specifically, for the natural setting that $α$ i…
