We study the linear contextual bandit problem with finite action sets. When the problem dimension is$d$, the time horizon is$T$, and there are$n \leq 2^{d/2}$candidate actions per time period, we 1) show that the minimax expected regret is$\Omega (\sqrt {dT (\log T) (\log n)})$for every algorithm, and 2) introduce a Variable-Confidence-Level (VCL) SupLinUCB algorithm whose regret matches the lower bound up to iterated logarithmic factors. Our algorithmic result saves two$\sqrt {\log T}$factors from previous analysis, and our information-theoretical lower bound also improves previous results by one$\sqrt {\log T}$factor, revealing a regret scaling quite different from classical multi-armed bandits in which no logarithmic$T$term is present in minimax regret. Our proof techniques include variable confidence levels and a careful analysis of layer sizes of SupLinUCB on the upper bound side, and delicately constructed adversarial sequences showing the tightness of elliptical potential lemmas on the lower bound side.

Linear contextual bandit is a class of sequential decision-making problems with important applications in recommendation systems, online advertising, healthcare, and other machine learning-related tasks. While there is much prior research, tight regret bounds of linear contextual bandit with infinite action sets remain open. In this paper, we consider the linear contextual bandit problem with (changing) infinite action sets. We prove a regret upper bound on the order of O(\sqrt{d^2T\log T}) \poly(\log\log T) where d is the domain dimension and T is the time horizon. Our upper bound matches the previous lower bound of \Omega(\sqrt{d^2 T\log T}) in [Li et al., 2019] up to iterated logarithmic terms.

We consider bandit optimization of a smooth reward function, where the goal is cumulative regret minimization. This problem has been studied for $\alpha$-Holder continuous (including Lipschitz) functions with $0<\alpha\leq 1$. Our main result is in generalization of the reward function to Holder space with exponent $\alpha>1$ to bridge the gap between Lipschitz bandits and infinitely-differentiable models such as linear bandits. For Holder continuous functions, approaches based on random sampling in bins of a discretized domain suffices as optimal. In contrast, we propose a class of two-layer algorithms that deploy misspecified linear/polynomial bandit algorithms in bins. We demonstrate that the proposed algorithm can exploit higher-order smoothness of the function by deriving a regret upper bound of $\tilde{O}(T^\frac{d+\alpha}{d+2\alpha})$ for when $\alpha>1$, which matches existing lower bound. We also study adaptation to unknown function smoothness over a continuous scale of Holder spaces indexed by $\alpha$, with a bandit model selection approach applied with our proposed two-layer algorithms. We show that it achieves regret rate that matches the existing lower bound for adaptation within the $\alpha\leq 1$ subset.

Summary of Contribution: Big data analytics has become essential for modern operations research and operations management applications. Statistics methods, such as nonparametric density and function estimation, play important roles in predictive and exploratory data analysis for economics and operations management problems. In this paper, we concentrate on efficiently computing local polynomial regression estimates. We significantly accelerate the computation of such local polynomial estimates by novel applications of multidimensional binary indexed trees ( Fenwick 1994 ) and lazy memory allocation via hashing. Both time and space complexity of our proposed algorithm are nearly linear in the number of inputs. Simulation results confirm the efficiency and effectiveness of our proposed methods.

In this paper, we consider the problem of online learning of Markov decision processes (MDPs) with very large state spaces. Under the assumptions of realizable function approximation and low Bellman ranks, we develop an online learning algorithm that learns the optimal value function while at the same time achieving very low cumulative regret during the learning process. Our learning algorithm, Adaptive Value-function Elimination (AVE), is inspired by the policy elimination algorithm proposed in (Jiang et al., 2017), known as OLIVE. One of our key technical contributions in AVE is to formulate the elimination steps in OLIVE as contextual bandit problems. This technique enables us to apply the active elimination and expert weighting methods from (Dudik et al., 2011), instead of the random action exploration scheme used in the original OLIVE algorithm, for more efficient exploration and better control of the regret incurred in each policy elimination step. To the best of our knowledge, this is the first root-n-regret result for reinforcement learning in stochastic MDPs with general value function approximation.

In this paper, we study the dynamic assortment optimization problem over a finite selling season of length $T$. At each time period, the seller offers an arriving customer an assortment of substitutable products under a cardinality constraint, and the customer makes the purchase among offered products according to a discrete choice model. Most existing work associates each product with a real-valued fixed mean utility and assumes a multinomial logit choice (MNL) model. In many practical applications, feature/contextual information of products is readily available. In this paper, we incorporate the feature information by assuming a linear relationship between the mean utility and the feature. In addition, we allow the feature information of products to change over time so that the underlying choice model can also be non-stationary. To solve the dynamic assortment optimization under this changing contextual MNL model, we need to simultaneously learn the underlying unknown coefficient and make the decision on the assortment. To this end, we develop an upper confidence bound (UCB) based policy and establish the regret bound on the order of $\tilde{O}(d\sqrt{T})$, where $d$ is the dimension of the feature and $\tilde{O}$ suppresses logarithmic dependence. We further establish a lower bound $\Omega(d\sqrt{T}/{K})$, where $K$ is the cardinality constraint of an offered assortment, which is usually small. When $K$ is a constant, our policy is optimal up to logarithmic factors. In the exploitation phase of the UCB algorithm, we need to solve a combinatorial optimization problem for assortment optimization based on the learned information. We further develop an approximation algorithm and an efficient greedy heuristic. The effectiveness of the proposed policy is further demonstrated by our numerical studies.

We study the linear contextual bandit problem with finite action sets. When the problem dimension is $d$, the time horizon is $T$, and there are $n \leq 2^{d/2}$ candidate actions per time period, we (1) show that the minimax expected regret is $\Omega(\sqrt{dT \log T \log n})$ for every algorithm, and (2) introduce a Variable-Confidence-Level (VCL) SupLinUCB algorithm whose regret matches the lower bound up to iterated logarithmic factors. Our algorithmic result saves two $\sqrt{\log T}$ factors from previous analysis, and our information-theoretical lower bound also improves previous results by one $\sqrt{\log T}$ factor, revealing a regret scaling quite different from classical multi-armed bandits in which no logarithmic $T$ term is present in minimax regret. Our proof techniques include variable confidence levels and a careful analysis of layer sizes of SupLinUCB on the upper bound side, and delicately constructed adversarial sequences showing the tightness of elliptical potential lemmas on the lower bound side.

We consider the problem of global optimization of an unknown non-convex smooth function with noisy zeroth-order feedback. We propose a local minimax framework to study the fundamental difficulty of optimizing smooth functions with adaptive function evaluations. We show that for functions with fast growth around their global minima, carefully designed optimization algorithms can identify a near global minimizer with many fewer queries than worst-case global minimax theory predicts. For the special case of strongly convex and smooth functions, our implied convergence rates match the ones developed for zeroth-order convex optimization problems. On the other hand, we show that in the worst case no algorithm can converge faster than the minimax rate of estimating an unknown function in the ℓ∞-norm. Finally, we show that non-adaptive algorithms, though optimal in a global minimax sense, do not attain the optimal local minimax rate.

Subspace clustering is the problem of partitioning unlabeled data points into a number of clusters so that data points within one cluster lie approximately on a low-dimensional linear subspace. In many practical scenarios, the dimensionality of data points to be clustered is compressed due to the constraints of measurement, computation, or privacy. In this paper, we study the theoretical properties of a popular subspace clustering algorithm named sparse subspace clustering (SSC) and establish formal success conditions of SSC on dimensionality-reduced data. Our analysis applies to the most general fully deterministic model, where both underlying subspaces and data points within each subspace are deterministically positioned, and also a wide range of dimensionality reduction techniques (e.g., Gaussian random projection, uniform subsampling, and sketching) that fall into a subspace embedding framework. Finally, we apply our analysis to a differentially private SSC algorithm and established both privacy and utility guarantees of the proposed method.

We consider the problem of optimizing a high-dimensional convex function using stochastic zeroth-order queries. Under sparsity assumptions on the gradients or function values, we present two algorithms: a successive component/feature selection algorithm and a noisy mirror descent algorithm using Lasso gradient estimates, and show that both algorithms have convergence rates that depend only logarithmically on the ambient dimension of the problem. Empirical results confirm our theoretical findings and show that the algorithms we design outperform classical zeroth-order optimization methods in the high-dimensional setting.

In this paper we consider the problem of allocation of measurement bits in order to reduce the statistical signal recovery error resulting from quantization error. We propose a continuous optimization problem that serves as a relaxation of the original combinatorial problem, which is amenable to classical continuous optimization solvers such as the gradient descent. We also design a “rounding” algorithm based on the idea of effective resistance sampling to turn the continuous fractional solution into a feasible bit allocation strategy with integer number of bits allocated to each design point.

A widespread folklore for explaining the success of Convolutional Neural Networks (CNNs) is that CNNs use a more compact representation than the Fully-connected Neural Network (FNN) and thus require fewer training samples to accurately estimate their parameters. We initiate the study of rigorously characterizing the sample complexity of estimating CNNs. We show that for an $m$-dimensional convolutional filter with linear activation acting on a $d$-dimensional input, the sample complexity of achieving population prediction error of $\epsilon$ is $\widetilde{O(m/\epsilon^2)$, whereas the sample-complexity for its FNN counterpart is lower bounded by $\Omega(d/\epsilon^2)$ samples. Since, in typical settings $m \ll d$, this result demonstrates the advantage of using a CNN. We further consider the sample complexity of estimating a one-hidden-layer CNN with linear activation where both the $m$-dimensional convolutional filter and the $r$-dimensional output weights are unknown. For this model, we show that the sample complexity is $\widetilde{O}\left((m+r)/\epsilon^2\right)$ when the ratio between the stride size and the filter size is a constant. For both models, we also present lower bounds showing our sample complexities are tight up to logarithmic factors. Our main tools for deriving these results are a localized empirical process analysis and a new lemma characterizing the convolutional structure. We believe that these tools may inspire further developments in understanding CNNs.

We consider the problem of global optimization of an unknown non-convex smooth function with noisy zeroth-order feedback. We propose a local minimax framework to study the fundamental difficulty of optimizing smooth functions with adaptive function evaluations. We show that for functions with fast growth around their global minima, carefully designed optimization algorithms can identify a near global minimizer with many fewer queries than worst-case global minimax theory predicts. For the special case of strongly convex and smooth functions, our implied convergence rates match the ones developed for zeroth-order convex optimization problems. On the other hand, we show that in the worst case no algorithm can converge faster than the minimax rate of estimating an unknown functions in linf-norm. Finally, we show that non-adaptive algorithms, although optimal in a global minimax sense, do not attain the optimal local minimax rate.

In this paper we consider the dynamic assortment selection problem under an uncapacitated multinomial-logit (MNL) model. By carefully analyzing a revenue potential function, we show that a trisection based algorithm achieves an item-independent regret bound of O(sqrt(T log log T), which matches information theoretical lower bounds up to iterated logarithmic terms. Our proof technique draws tools from the unimodal/convex bandit literature as well as adaptive confidence parameters in minimax multi-armed bandit problems.

Supervised topic models simultaneously model the latent topic structure of large collections of documents and a response variable associated with each document. Existing inference methods are based on variational approximation or Monte Carlo sampling, which often suffers from the local minimum defect. Spectral methods have been applied to learn unsupervised topic models, such as latent Dirichlet allocation (LDA), with provable guarantees. This paper investigates the possibility of applying spectral methods to recover the parameters of supervised LDA (sLDA). We first present a two-stage spectral method, which recovers the parameters of LDA followed by a power update method to recover the regression model parameters. Then, we further present a single-phase spectral algorithm to jointly recover the topic distribution matrix as well as the regression weights. Our spectral algorithms are provably correct and computationally efficient. We prove a sample complexity bound for each algorithm and subsequently derive a sufficient condition for the identifiability of sLDA. Thorough experiments on synthetic and real-world datasets verify the theory and demonstrate the practical effectiveness of the spectral algorithms. In fact, our results on a large-scale review rating dataset demonstrate that our single-phase spectral algorithm alone gets comparable or even better performance than state-of-the-art methods, while previous work on spectral methods has rarely reported such promising performance.

We consider computationally tractable methods for the experimental design problem, where k out of n design points of dimension p are selected so that certain optimality criteria are approximately satisfied. Our algorithm finds a $(1+\epsilon)$-approximate optimal design when k is a linear function of p; in contrast, existing results require k to be super-linear in p. Our algorithm also handles all popular optimality criteria, while existing ones only handle one or two such criteria. Numerical results on synthetic and real-world design problems verify the practical effectiveness of the proposed algorithm.

We show that given an estimate $\widehat{\mat A}$ that is close to a general high-rank positive semi-definite (PSD) matrix $\mat A$ in spectral norm (i.e., $\|\widehat{\mat A}-\mat A\|_2 \leq \delta$), the simple truncated Singular Value Decomposition of $\widehat{\mat A}$ produces a multiplicative approximation of $\mat A$ in Frobenius norm. This observation leads to many interesting results on general high-rank matrix estimation problems: 1.High-rank matrix completion: we show that it is possible to recover a {general high-rank matrix} $\mat A$ up to $(1+\varepsilon)$ relative error in Frobenius norm from partial observations, with sample complexity independent of the spectral gap of $\mat A$. 2.High-rank matrix denoising: we design algorithms that recovers a matrix $\mat A$ with relative error in Frobenius norm from its noise-perturbed observations, without assuming $\mat A$ is exactly low-rank. 3.Low-dimensional estimation of high-dimensional covariance: given $N$ i.i.d.~samples of dimension $n$ from $\mathcal N_n(\mat 0,\mat A)$, we show that it is possible to estimate the covariance matrix $\mat A$ with relative error in Frobenius norm with $N\approx n$,improving over classical covariance estimation results which requires $N\approx n^2$.

We derive computationally tractable methods to select a small subset of experiment settings from a large pool of given design points. The primary focus is on linear regression models, while the technique extends to generalized linear models and Delta's method (estimating functions of linear regression models) as well. The algorithms are based on a continuous relaxation of an otherwise intractable combinatorial optimization problem, with sampling or greedy procedures as post-processing steps. Formal approximation guarantees are established for both algorithms, and numerical results on both synthetic and real-world data confirm the effectiveness of the proposed methods.

We present a simple noise-robust margin-based active learn-ing algorithm to find homogeneous (passing the origin) linearseparators and analyze its error convergence when labels arecorrupted by noise. We show that when the imposed noisesatisfies the Tsybakov low noise condition (Mammen, Tsy-bakov, and others 1999; Tsybakov 2004) the algorithm is ableto adapt to unknown level of noise and achieves optimal sta-tistical rate up to polylogarithmic factors. We also derive lower bounds for margin based active learningalgorithms under Tsybakov noise conditions (TNC) for themembership query synthesis scenario (Angluin 1988). Ourresult implies lower bounds for the stream based selectivesampling scenario (Cohn 1990) under TNC for some fairlysimple data distributions. Quite surprisingly, we show that thesample complexity cannot be improved even if the underly-ing data distribution is as simple as the uniform distributionon the unit ball. Our proof involves the construction of a well-separated hypothesis set on the d-dimensional unit ball alongwith carefully designed label distributions for the Tsybakovnoise condition. Our analysis might provide insights for otherforms of lower bounds as well.

Subspace clustering is the problem of clustering data points into a union of low-dimensional linear/affine subspaces. It is the mathematical abstraction of many important problems in computer vision, image processing and machine learning. A line of recent work [4, 19, 24, 20] provided strong theoretical guarantee for sparse subspace cluster- ing [4], the state-of-the-art algorithm for sub- space clustering, on both noiseless and noisy data sets. It was shown that under mild conditions, with high probability no two points from different subspaces are clustered together. Such guarantee, however, is not sufficient for the clustering to be correct, due to the notorious “graph connectivity problem” [15]. In this paper, we investigate the graph connectivity problem for noisy sparse sub-space clustering and show that a simple post-processing procedure is capable of delivering consistent clustering under certain “general position” or “restricted eigenvalue” assumptions. We also show that our condition is almost tight with adversarial noise perturbation by constructing a counter-example. These results provide the first exact clustering guarantee of noisy SSC for subspaces of dimension greater then 3.

We consider the \emphnoisy power method algorithm, which has wide applications in machine learning and statistics, especially those related to principal component analysis (PCA) under resource (communication, memory or privacy) constraints. Existing analysis of the noisy power method shows an unsatisfactory dependency over the “consecutive" spectral gap (\sigma_k-\sigma_k+1) of an input data matrix, which could be very small and hence limits the algorithm’s applicability. In this paper, we present a new analysis of the noisy power method that achieves improved gap dependency for both sample complexity and noise tolerance bounds. More specifically, we improve the dependency over (\sigma_k-\sigma_k+1) to dependency over (\sigma_k-\sigma_q+1), where q is an intermediate algorithm parameter and could be much larger than the target rank k. Our proofs are built upon a novel characterization of proximity between two subspaces that differ from canonical angle characterizations analyzed in previous works. Finally, we apply our improved bounds to distributed private PCA and memory-efficient streaming PCA and obtain bounds that are superior to existing results in the literature.

Recommendation and collaborative filtering systems are important in modern information and e-commerce applications. As these systems are becoming increasingly popular in industry, their outputs could affect business decision making, introducing incentives for an adversarial party to compromise the availability or integrity of such systems. We introduce a data poisoning attack on collaborative filtering systems. We demonstrate how a powerful attacker with full knowledge of the learner can generate malicious data so as to maximize his/her malicious objectives, while at the same time mimicking normal user behaviors to avoid being detected. While the complete knowledge assumption seems extreme, it enables a robust assessment of the vulnerability of collaborative filtering schemes to highly motivated attacks. We present efficient solutions for two popular factorization-based collaborative filtering algorithms: the alternative minimization formulation and the nuclear norm minimization method. Finally, we test the effectiveness of our proposed algorithms on real-world data and discuss potential defensive strategies.

Column subset selection of massive data matrices has found numerous applications in real-world data systems. In this paper, we propose and analyze two sampling based algorithms for column subset selection without access to the complete input matrix. To our knowledge, these are the first algorithms for column subset selection with missing data that are provably correct. The proposed methods work for row/column coherent matrices by employing the idea of adaptive sampling. Furthermore, when the input matrix has a noisy low-rank structure, one algorithm enjoys a relative error bound.

Subspace clustering groups data into several lowrank subspaces. In this paper, we propose a theoretical framework to analyze a popular optimization-based algorithm, Sparse Subspace Clustering (SSC), when the data dimension is compressed via some random projection algorithms. We show SSC provably succeeds if the random projection is a subspace embedding, which includes random Gaussian projection, uniform row sampling, FJLT, sketching, etc. Our analysis applies to the most general deterministic setting and is able to handle both adversarial and stochastic noise. It also results in the first algorithm for privacy-preserved subspace clustering.

Subspace clustering separates data points approximately lying on union of affine subspaces into several clusters. This paper presents a novel nonparametric Bayesian subspace clustering model that infers both the number of subspaces and the dimension of each subspace from the observed data. Though the posterior inference is hard, our model leads to a very efficient deterministic algorithm, DP-space, which retains the nonparametric ability under a small-variance asymptotic analysis. DP-space monotonically minimizes an intuitive objective with an explicit tradeoff between data fitness and model complexity. Experimental results demonstrate that DP-space outperforms various competitors in terms of clustering accuracy and at the same time it is highly efficient.

Subspace clustering is an unsupervised learning problem that aims at grouping data points into multiple clusters'' so that data points in a single cluster lie approximately on a low-dimensional linear subspace. It is originally motivated by 3D motion segmentation in computer vision, but has recently been generically applied to a wide range of statistical machine learning problems, which often involves sensitive datasets about human subjects. This raises a dire concern for data privacy. In this work, we build on the framework ofdifferential privacy'' and present two provably private subspace clustering algorithms. We demonstrate via both theory and experiments that one of the presented methods enjoys formal privacy and utility guarantees; the other one asymptotically preserves differential privacy while having good performance in practice. Along the course of the proof, we also obtain two new provable guarantees for the agnostic subspace clustering and the graph connectivity problem which might be of independent interests.

Infinite SVM (iSVM) is a Dirichlet process (DP) mixture of large-margin classifiers. Though flexible in learning nonlinear classifiers and discovering latent clustering structures, iSVM has a difficult inference task and existing methods could hinder its applicability to large-scale problems. This paper presents a small-variance asymptotic analysis to derive a simple and efficient algorithm, which monotonically optimizes a max-margin DP-means (M2DPM) problem, an extension of DP-means for both predictive learning and descriptive clustering. Our analysis is built on Gibbs infinite SVMs, an alternative DP mixture of large-margin machines, which admits a partially collapsed Gibbs sampler without truncation by exploring data augmentation techniques. Experimental results show that M2DPM runs much faster than similar algorithms without sacrificing prediction accuracies.

Ranking has been extensively studied in information retrieval, machine learning and statistics. A central problem in ranking is to design a ranking measure for evaluation of ranking functions. State of the art leaning to rank methods often train a ranking function by using a ranking measure as the objective to maximize. In this paper we study, from a theoretical perspective, the widely used NDCG type ranking measures. We analyze the behavior of these ranking measures as the number of objects to rank getting large. We first show that, whatever the ranking function is, the standard NDCG which adopts a logarithmic discount, converges to 1 as the number of items to rank goes to infinity. On the first sight, this result seems to imply that NDCG cannot distinguish good and bad ranking functions, contradicting to the empirical success of NDCG in many applications. Our next main result is a theorem which shows that although NDCG converge to the same limit for all ranking functions, it has distinguishability for ranking functions in a strong sense. We then investigate NDCG with other possible discount. Specifically we characterize the class of feasible discount functions for NDCG. We also compare the limiting behavior and the power of distinguishability of these feasible NDCG type measures to the standard NDCG. We next turn to the cut-off version of NDCG, i.e., NDCG@k. The most popular NDCG@k uses a combination of a slow logarithmic decay and a hard cut-off as its discount. So a natural question is why not simply use a smooth discount with fast decay? We show that if the decay is too fast, then the NDCG measure does not have strong power of distinguishability and even not converge. Finally, feasible NDCG@k are also discussed.