In this work we solve the problem of robustly learning a high-dimensional Gaussian mixture model with $k$ components from $ε$-corrupted samples up to accuracy $\widetilde{O}(ε)$ in total variation distance for any constant $k$ and with mild assumptions on the mixture. This robustness guarantee is optimal up to polylogarithmic factors. The main challenge is that most earlier works rely on learning individual components in the mixture, but this is impossible in our setting, at least for the types of strong robustness guarantees we are aiming for. Instead we introduce a new framework which we call {\em strong observability} that gives us a route to circumvent this obstacle.
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{…
Gaussian Mixture Model with unknown diagonal covariances via continuous sparse regularization
Centrale Lyon, CNRS UMR 5208, Institut Camille Jordan（里昂中央理工学院，法国国家科学研究中心联合研究实验室5208，卡米尔·乔丹研究所）；Institut Universitaire de France (IUF)（法兰西学院）；Univ. Claude Bernard, CNRS UMR 5208, Institut Camille Jordan（克洛德·贝尔纳大学，法国国家科学研究中心联合研究实验室5208，卡米尔·乔丹研究所）
Community detection tasks have received a lot of attention across statistics, machine learning, and information theory with a large body of work concentrating on theoretical guarantees for the stochastic block model. One line of recent work has focused on modeling the spectral embedding of a network using Gaussian mixture models (GMMs) in scaling regimes where the ability to detect community memberships improves with the size of the network. However, these regimes are not very realistic. This paper provides tractable methodology motivated by new theoretical results for networks with non-vanish…
In this paper, We propose a general Riemannian proximal optimization algorithm with guaranteed convergence to solve Markov decision process (MDP) problems. To model policy functions in MDP, we employ Gaussian mixture model (GMM) and formulate it as a nonconvex optimization problem in the Riemannian space of positive semidefinite matrices. For two given policy functions, we also provide its lower bound on policy improvement by using bounds derived from the Wasserstein distance of GMMs. Preliminary experiments show the efficacy of our proposed Riemannian proximal policy optimization algorithm.
University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；Shanghai University of Finance and Economics（上海财经大学）；Institute of Advanced Study（高等研究院）；Shanghai Jiao Tong University（上海交通大学）
We study the problem of learning Bayesian networks where an $ε$-fraction of the samples are adversarially corrupted. We focus on the fully-observable case where the underlying graph structure is known. In this work, we present the first nearly-linear time algorithm for this problem with a dimension-independent error guarantee. Previous robust algorithms with comparable error guarantees are slower by at least a factor of $(d/ε)$, where $d$ is the number of variables in the Bayesian network and $ε$ is the fraction of corrupted samples. Our algorithm and analysis are considerably simpler than tho…
Riemannian Gradient Descent for Gaussian Mixture Models with unknown diagonal covariances
Centrale Lyon, INSA Lyon, Université Lyon 1, Université Jean Monnet, CNRS, ICJ UMR5208（里昂中央理工学院、里昂国立应用科学学院、里昂第一大学、让·莫内大学、法国国家科学研究中心、ICJ UMR5208）；Institut Universitaire de France (IUF)（法兰西学院）
Learning parameters from voluminous data can be prohibitive in terms of memory and computational requirements. We propose a "compressive learning" framework where we estimate model parameters from a sketch of the training data. This sketch is a collection of generalized moments of the underlying probability distribution of the data. It can be computed in a single pass on the training set, and is easily computable on streams or distributed datasets. The proposed framework shares similarities with compressive sensing, which aims at drastically reducing the dimension of high-dimensional signals w…
We consider clustering based on significance tests for Gaussian Mixture Models (GMMs). Our starting point is the SigClust method developed by Liu et al. (2008), which introduces a test based on the k-means objective (with k = 2) to decide whether the data should be split into two clusters. When applied recursively, this test yields a method for hierarchical clustering that is equipped with a significance guarantee. We study the limiting distribution and power of this approach in some examples and show that there are large regions of the parameter space where the power is low. We then introduce…
Differentially Private Distribution Release of Gaussian Mixture Models via KL-Divergence Minimization
State Key Laboratory of Internet of Things for Smart City and the Department of Electrical and Computer Engineering, University of Macau（物联网智能城市国家重点实验室和澳门大学电子与计算机工程系）；Department of Electrical and Computer Engineering, Cornell Tech, Cornell University（电气与计算机工程系，康奈尔科技，康奈尔大学）；Computing Sciences Research, Lawrence Berkeley National Laboratory（计算科学研究所，劳伦斯伯克利国家实验室）
Duke University（杜克大学）；University of Southern California（南加州大学）；University of California, San Diego（加州大学圣地亚哥分校）
We investigate the problem of learning Bayesian networks in a robust model where an $ε$-fraction of the samples are adversarially corrupted. In this work, we study the fully observable discrete case where the structure of the network is given. Even in this basic setting, previous learning algorithms either run in exponential time or lose dimension-dependent factors in their error guarantees. We provide the first computationally efficient robust learning algorithm for this problem with dimension-independent error guarantees. Our algorithm has near-optimal sample complexity, runs in polynomial t…
University of Wisconsin, Madison（威斯康星大学麦迪逊分校）；University of California, San Diego（加利福尼亚大学圣迭戈分校）；Microsoft Research（微软研究院）；Stanford University（斯坦福大学）
We study the problem of list-decodable mean estimation, where an adversary can corrupt a majority of the dataset. Specifically, we are given a set $T$ of $n$ points in $\mathbb{R}^d$ and a parameter $0< α<\frac 1 2$ such that an $α$-fraction of the points in $T$ are i.i.d. samples from a well-behaved distribution $\mathcal{D}$ and the remaining $(1-α)$-fraction are arbitrary. The goal is to output a small list of vectors, at least one of which is close to the mean of $\mathcal{D}$. We develop new algorithms for list-decodable mean estimation, achieving nearly-optimal statistical guarantees, wi…
Duke University（杜克大学）；University of Southern California（南加州大学）
We study the fundamental problem of high-dimensional mean estimation in a robust model where a constant fraction of the samples are adversarially corrupted. Recent work gave the first polynomial time algorithms for this problem with dimension-independent error guarantees for several families of structured distributions. In this work, we give the first nearly-linear time algorithms for high-dimensional robust mean estimation. Specifically, we focus on distributions with (i) known covariance and sub-gaussian tails, and (ii) unknown bounded covariance. Given $N$ samples on $\mathbb{R}^d$, an $ε$-…
Adobe Research（奥多比研究院）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；Boston University（波士顿大学）；MIT（麻省理工学院）
Given a matrix $A\in \mathbb{R}^{n\times d}$ and a vector $b\in \mathbb{R}^n$, we consider the regression problem with $\ell_\infty$ guarantees: finding a vector $x'\in \mathbb{R}^d$ such that $ \|x'-x^*\|_\infty \leq \fracε{\sqrt{d}}\cdot \|Ax^*-b\|_2\cdot \|A^\dagger\|$ where $x^*=\arg\min_{x\in \mathbb{R}^d}\|Ax-b\|_2$. One popular approach for solving such $\ell_2$ regression problem is via sketching: picking a structured random matrix $S\in \mathbb{R}^{m\times n}$ with $m\ll n$ and $SA$ can be quickly computed, solve the ``sketched'' regression problem $\arg\min_{x\in \mathbb{R}^d} \|SAx-…
University of Southern California（南加利福尼亚大学）；University of California, San Diego（加利福尼亚大学圣迭戈分校）
We describe a general technique that yields the first {\em Statistical Query lower bounds} for a range of fundamental high-dimensional learning problems involving Gaussian distributions. Our main results are for the problems of (1) learning Gaussian mixture models (GMMs), and (2) robust (agnostic) learning of a single unknown Gaussian distribution. For each of these problems, we show a {\em super-polynomial gap} between the (information-theoretic) sample complexity and the computational complexity of {\em any} Statistical Query algorithm for the problem. Our SQ lower bound for Problem (1) is q…
University of California, Berkeley（加州大学伯克利分校）；Peking University（北京大学）；Peng Cheng Laboratory（鹏城实验室）；University of Washington（华盛顿大学）
Policy optimization methods are one of the most widely used classes of Reinforcement Learning (RL) algorithms. However, theoretical understanding of these methods remains insufficient. Even in the episodic (time-inhomogeneous) tabular setting, the state-of-the-art theoretical result of policy-based method in \citet{shani2020optimistic} is only $\tilde{O}(\sqrt{S^2AH^4K})$ where $S$ is the number of states, $A$ is the number of actions, $H$ is the horizon, and $K$ is the number of episodes, and there is a $\sqrt{SH}$ gap compared with the information theoretic lower bound $\tildeΩ(\sqrt{SAH^3K}…
Recent work of Erlingsson, Feldman, Mironov, Raghunathan, Talwar, and Thakurta [EFMRTT19] demonstrates that random shuffling amplifies differential privacy guarantees of locally randomized data. Such amplification implies substantially stronger privacy guarantees for systems in which data is contributed anonymously [BEMMRLRKTS17] and has lead to significant interest in the shuffle model of privacy [CSUZZ19; EFMRTT19]. We show that random shuffling of $n$ data records that are input to $\varepsilon_0$-differentially private local randomizers results in an $(O((1-e^{-\varepsilon_0})\sqrt{\frac{e…
Boston University（波士顿大学）；Northeastern University（东北大学）
In this work, we give a new parallel algorithm for the problem of maximizing a non-monotone diminishing returns submodular function subject to a cardinality constraint. For any desired accuracy $ε$, our algorithm achieves a $1/e - ε$ approximation using $O(\log{n} \log(1/ε) / ε^3)$ parallel rounds of function evaluations. The approximation guarantee nearly matches the best approximation guarantee known for the problem in the sequential setting and the number of parallel rounds is nearly-optimal for any constant $ε$. Previous algorithms achieve worse approximation guarantees using $Ω(\log^2{n})…
We initiate the rigorous study of classification in semimetric spaces, which are point sets with a distance function that is non-negative and symmetric, but need not satisfy the triangle inequality. For metric spaces, the doubling dimension essentially characterizes both the runtime and sample complexity of classification algorithms --- yet we show that this is not the case for semimetrics. Instead, we define the {\em density dimension} and discover that it plays a central role in the statistical and algorithmic feasibility of learning in semimetric spaces. We present nearly optimal sample com…
We propose Byzantine-robust federated learning protocols with nearly optimal statistical rates. In contrast to prior work, our proposed protocols improve the dimension dependence and achieve a tight statistical rate in terms of all the parameters for strongly convex losses. We benchmark against competing protocols and show the empirical superiority of the proposed protocols. Finally, we remark that our protocols with bucketing can be naturally combined with privacy-guaranteeing procedures to introduce security against a semi-honest server. The code for evaluation is provided in https://github.…
University of California Berkeley（加州大学伯克利分校）；EPFL（洛桑联邦理工学院）
We study the problem of high-dimensional robust linear regression where a learner is given access to $n$ samples from the generative model $Y = \langle X,w^* \rangle + ε$ (with $X \in \mathbb{R}^d$ and $ε$ independent), in which an $η$ fraction of the samples have been adversarially corrupted. We propose estimators for this problem under two settings: (i) $X$ is L4-L2 hypercontractive, $\mathbb{E} [XX^\top]$ has bounded condition number and $ε$ has bounded variance and (ii) $X$ is sub-Gaussian with identity second moment and $ε$ is sub-Gaussian. In both settings, our estimators: (a) Achieve op…
We design a new, fast algorithm for agnostically learning univariate probability distributions whose densities are well approximated by piecewise polynomial functions. Let $f$ be the density function of an arbitrary univariate distribution, and suppose that $f$ is $\mathrm{OPT}$-close in $L_1$-distance to an unknown piecewise polynomial function with $t$ interval pieces and degree $d$. Our algorithm draws $n = O(t(d+1)/ε^2)$ samples from $f$, runs in time $\tilde{O}(n \cdot \mathrm{poly}(d))$, and with probability at least $9/10$ outputs an $O(t)$-piecewise degree-$d$ hypothesis $h$ that is $4…
Princeton University（普林斯顿大学）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）
Mixtures of Linear Regressions (MLR) is an important mixture model with many applications. In this model, each observation is generated from one of the several unknown linear regression components, where the identity of the generated component is also unknown. Previous works either assume strong assumptions on the data distribution or have high complexity. This paper proposes a fixed parameter tractable algorithm for the problem under general conditions, which achieves global convergence and the sample complexity scales nearly linearly in the dimension. In particular, different from previous w…
University of Science and Technology Beijing（北京科技大学）；Tsinghua University（清华大学）；University of California Berkeley（加州大学伯克利分校）；Beijing Idriverplus Technology Co., Ltd.（北京智行者科技有限公司）
This paper presents the Relaxed Continuous-Time Actor-critic (RCTAC) algorithm, a method for finding the nearly optimal policy for nonlinear continuous-time (CT) systems with known dynamics and infinite horizon, such as the path-tracking control of vehicles. RCTAC has several advantages over existing adaptive dynamic programming algorithms for CT systems. It does not require the ``admissibility" of the initialized policy or the input-affine nature of controlled systems for convergence. Instead, given any initial policy, RCTAC can converge to an admissible, and subsequently nearly optimal polic…
In this paper, we study the problem of stochastic linear bandits with finite action sets. Most of existing work assume the payoffs are bounded or sub-Gaussian, which may be violated in some scenarios such as financial markets. To settle this issue, we analyze the linear bandits with heavy-tailed payoffs, where the payoffs admit finite $1+ε$ moments for some $ε\in(0,1]$. Through median of means and dynamic truncation, we propose two novel algorithms which enjoy a sublinear regret bound of $\widetilde{O}(d^{\frac{1}{2}}T^{\frac{1}{1+ε}})$, where $d$ is the dimension of contextual information and…
We study nonlinear regression of real valued data in an individual sequence manner, where we provide results that are guaranteed to hold without any statistical assumptions. We address the convergence and undertraining issues of conventional nonlinear regression methods and introduce an algorithm that elegantly mitigates these issues via an incremental hierarchical structure, (i.e., via an incremental decision tree). Particularly, we present a piecewise linear (or nonlinear) regression algorithm that partitions the regressor space in a data driven manner and learns a linear model at each regio…
Ariel University（阿里埃勒大学）；Ben-Gurion University of the Negev（内盖夫本-古里安大学）；Tel-Aviv University（特拉维夫大学）
We present the first sample compression algorithm for nearest neighbors with non-trivial performance guarantees. We complement these guarantees by demonstrating almost matching hardness lower bounds, which show that our bound is nearly optimal. Our result yields new insight into margin-based nearest neighbor classification in metric spaces and allows us to significantly sharpen and simplify existing bounds. Some encouraging empirical results are also presented.
Rice University（莱斯大学）；University of Washington（华盛顿大学）；University of Wisconsin– Madison（威斯康星大学麦迪逊分校）
The level set estimation problem seeks to find all points in a domain ${\cal X}$ where the value of an unknown function $f:{\cal X}\rightarrow \mathbb{R}$ exceeds a threshold $α$. The estimation is based on noisy function evaluations that may be acquired at sequentially and adaptively chosen locations in ${\cal X}$. The threshold value $α$ can either be \emph{explicit} and provided a priori, or \emph{implicit} and defined relative to the optimal function value, i.e. $α= (1-ε)f(x_\ast)$ for a given $ε> 0$ where $f(x_\ast)$ is the maximal function value and is unknown. In this work we provide a …
Tsinghua University（清华大学）；University of Washington（华盛顿大学）
We study the reward-free reinforcement learning framework, which is particularly suitable for batch reinforcement learning and scenarios where one needs policies for multiple reward functions. This framework has two phases. In the exploration phase, the agent collects trajectories by interacting with the environment without using any reward signal. In the planning phase, the agent needs to return a near-optimal policy for arbitrary reward functions. We give a new efficient algorithm, \textbf{S}taged \textbf{S}ampling + \textbf{T}runcated \textbf{P}lanning (\algoname), which interacts with the …
