arXiv subjects

Gábor Lugosi

Publications and source records attributed to Gábor Lugosi.

At least 37 records · Page 2Linked to original sources

arXiv2022

Generalization Bounds via Convex Analysis

Since the celebrated works of Russo and Zou (2016,2019) and Xu and Raginsky (2017), it has been well known that the generalization error of supervised learning algorithms can be bounded in terms of the mutual information between their input and the output, given that the loss of any fixed hypothesis has a subgaussian tail. In this work, we generalize this result beyond the standard choice of Shannon's mutual information to measure the dependence between the input and the output. Our main result shows that it is indeed possible to replace the mutual information by any strongly convex function of the joint input-output distribution, with the subgaussianity condition on the losses replaced by a bound on an appropriately chosen norm capturing the geometry of the dependence measure. This allows us to derive a range of generalization bounds that are either entirely new or strengthen previously known ones. Examples include bounds stated in terms of $p$-norm divergences and the Wasserstein-2 distance, which are respectively applicable for heavy-tailed loss distributions and highly smooth loss functions. Our analysis is entirely based on elementary tools from convex analysis by tracking the growth of a potential function associated with the dependence measure and the loss function.

stat.ML↗

arXiv2021

Bandit problems with fidelity rewards

The fidelity bandits problem is a variant of the $K$-armed bandit problem in which the reward of each arm is augmented by a fidelity reward that provides the player with an additional payoff depending on how 'loyal' the player has been to that arm in the past. We propose two models for fidelity. In the loyalty-points model the amount of extra reward depends on the number of times the arm has previously been played. In the subscription model the additional reward depends on the current number of consecutive draws of the arm. We consider both stochastic and adversarial problems. Since single-arm strategies are not always optimal in stochastic problems, the notion of regret in the adversarial setting needs careful adjustment. We introduce three possible notions of regret and investigate which can be bounded sublinearly. We study in detail the special cases of increasing, decreasing and coupon (where the player gets an additional reward after every $m$ plays of an arm) fidelity rewards. For the models which do not necessarily enjoy sublinear regret, we provide a worst case lower bound. For those models which exhibit sublinear regret, we provide algorithms and bound their regret.

stat.ML↗

arXiv2021

Learning partial correlation graphs and graphical models by covariance queries

We study the problem of recovering the structure underlying large Gaussian graphical models or, more generally, partial correlation graphs. In high-dimensional problems it is often too costly to store the entire sample covariance matrix. We propose a new input model in which one can query single entries of the covariance matrix. We prove that it is possible to recover the support of the inverse covariance matrix with low query and computational complexity. Our algorithms work in a regime when this support is represented by tree-like graphs and, more generally, for graphs of small treewidth. Our results demonstrate that for large classes of graphs, the structure of the corresponding partial correlation graphs can be determined much faster than even computing the empirical covariance matrix.

math.ST↗

arXiv2021

Learning to maximize global influence from local observations

We study a family online influence maximization problems where in a sequence of rounds $t=1,\ldots,T$, a decision maker selects one from a large number of agents with the goal of maximizing influence. Upon choosing an agent, the decision maker shares a piece of information with the agent, which information then spreads in an unobserved network over which the agents communicate. The goal of the decision maker is to select the sequence of agents in a way that the total number of influenced nodes in the network. In this work, we consider a scenario where the networks are generated independently for each $t$ according to some fixed but unknown distribution, so that the set of influenced nodes corresponds to the connected component of the random graph containing the vertex corresponding to the selected agent. Furthermore, we assume that the decision maker only has access to limited feedback: instead of making the unrealistic assumption that the entire network is observable, we suppose that the available feedback is generated based on a small neighborhood of the selected vertex. Our results show that such partial local observations can be sufficient for maximizing global influence. We model the underlying random graph as a sparse inhomogeneous Erdős--Rényi graph, and study three specific families of random graph models in detail: stochastic block models, Chung--Lu models and Kronecker random graphs. We show that in these cases one may learn to maximize influence by merely observing the degree of the selected vertex in the generated random graph. We propose sequential learning algorithms that aim at maximizing influence, and provide their theoretical analysis in both the subcritical and supercritical regimes of all considered models.

cs.LG↗

arXiv2021

Inferring the mixing properties of an ergodic process

We propose strongly consistent estimators of the $\ell_1$ norm of the sequence of $α$-mixing (respectively $β$-mixing) coefficients of a stationary ergodic process. We further provide strongly consistent estimators of individual $α$-mixing (respectively $β$-mixing) coefficients for a subclass of stationary $α$-mixing (respectively $β$-mixing) processes with summable sequences of mixing coefficients. The estimators are in turn used to develop strongly consistent goodness-of-fit hypothesis tests. In particular, we develop hypothesis tests to determine whether, under the same summability assumption, the $α$-mixing (respectively $β$-mixing) coefficients of a process are upper bounded by a given rate function. Moreover, given a sample generated by a (not necessarily mixing) stationary ergodic process, we provide a consistent test to discern the null hypothesis that the $\ell_1$ norm of the sequence $\boldsymbolα$ of $α$-mixing coefficients of the process is bounded by a given threshold $γ\in [0,\infty)$ from the alternative hypothesis that $\left\lVert \boldsymbolα \right\rVert> γ$. An analogous goodness-of-fit test is proposed for the $\ell_1$ norm of the sequence of $β$-mixing coefficients of a stationary ergodic process. Moreover, the procedure gives rise to an asymptotically consistent test for independence.

math.ST↗

arXiv2020

Noise sensitivity of the top eigenvector of a Wigner matrix

We investigate the noise sensitivity of the top eigenvector of a Wigner matrix in the following sense. Let $v$ be the top eigenvector of an $N\times N$ Wigner matrix. Suppose that $k$ randomly chosen entries of the matrix are resampled, resulting in another realization of the Wigner matrix with top eigenvector $v^{[k]}$. We prove that, with high probability, when $k \ll N^{5/3-o(1)}$, then $v$ and $v^{[k]}$ are almost collinear and when $k\gg N^{5/3}$, then $v^{[k]}$ is almost orthogonal to $v$.

math.PR↗

arXiv2020

Benign Overfitting in Linear Regression

The phenomenon of benign overfitting is one of the key mysteries uncovered by deep learning methodology: deep neural networks seem to predict well, even with a perfect fit to noisy training data. Motivated by this phenomenon, we consider when a perfect fit to training data in linear regression is compatible with accurate prediction. We give a characterization of linear regression problems for which the minimum norm interpolating prediction rule has near-optimal prediction accuracy. The characterization is in terms of two notions of the effective rank of the data covariance. It shows that overparameterization is essential for benign overfitting in this setting: the number of directions in parameter space that are unimportant for prediction must significantly exceed the sample size. By studying examples of data covariance properties that this characterization shows are required for benign overfitting, we find an important role for finite-dimensional data: the accuracy of the minimum norm interpolating prediction rule approaches the best possible accuracy for a much narrower range of properties of the data distribution when the data lies in an infinite dimensional space versus when the data lies in a finite dimensional space whose dimension grows faster than the sample size.

stat.ML↗

arXiv2018

Concentration of the spectral norm of Erdős-Rényi random graphs

We present results on the concentration properties of the spectral norm $\|A_p\|$ of the adjacency matrix $A_p$ of an Erdős-Rényi random graph $G(n,p)$. First we consider the Erdős-Rényi random graph process and prove that $\|A_p\|$ is uniformly concentrated over the range $p\in [C\log n/n,1]$. The analysis is based on delocalization arguments, uniform laws of large numbers, together with the entropy method to prove concentration inequalities. As an application of our techniques we prove sharp sub-Gaussian moment inequalities for $\|A_p\|$ for all $p\in [c\log^3n/n,1]$ that improve the general bounds of Alon, Krivelevich, and Vu (2001) and some of the more recent results of Erdős et al. (2013). Both results are consistent with the asymptotic result of Füredi and Komlós (1981) that holds for fixed $p$ as $n\to \infty$.

math.PR↗

arXiv2018

Near-optimal mean estimators with respect to general norms

We study the problem of estimating the mean of a random vector in $\mathbb{R}^d$ based on an i.i.d.\ sample, when the accuracy of the estimator is measured by a general norm on $\mathbb{R}^d$. We construct an estimator (that depends on the norm) that achieves an essentially optimal accuracy/confidence tradeoff under the only assumption that the random vector has a well-defined covariance matrix. The estimator is based on the construction of a uniform median-of-means estimator in a class of real valued functions that may be of independent interest.

math.ST↗

arXiv2018

Online Influence Maximization with Local Observations

We consider an online influence maximization problem in which a decision maker selects a node among a large number of possibilities and places a piece of information at the node. The node transmits the information to some others that are in the same connected component in a random graph. The goal of the decision maker is to reach as many nodes as possible, with the added complication that feedback is only available about the degree of the selected node. Our main result shows that such local observations can be sufficient for maximizing global influence in two broadly studied families of random graph models: stochastic block models and Chung--Lu models. With this insight, we propose a bandit algorithm that aims at maximizing local (and thus global) influence, and provide its theoretical analysis in both the subcritical and supercritical regimes of both considered models. Notably, our performance guarantees show no explicit dependence on the total number of nodes in the network, making our approach well-suited for large-scale applications.

cs.LG↗

arXiv2017

Regularization, sparse recovery, and median-of-means tournaments

A regularized risk minimization procedure for regression function estimation is introduced that achieves near optimal accuracy and confidence under general conditions, including heavy-tailed predictor and response variables. The procedure is based on median-of-means tournaments, introduced by the authors in [8]. It is shown that the new procedure outperforms standard regularized empirical risk minimization procedures such as lasso or slope in heavy-tailed problems.

math.ST↗

arXiv2017

Boltzmann Exploration Done Right

Boltzmann exploration is a classic strategy for sequential decision-making under uncertainty, and is one of the most standard tools in Reinforcement Learning (RL). Despite its widespread use, there is virtually no theoretical understanding about the limitations or the actual benefits of this exploration scheme. Does it drive exploration in a meaningful way? Is it prone to misidentifying the optimal actions or spending too much time exploring the suboptimal ones? What is the right tuning for the learning rate? In this paper, we address several of these questions in the classic setup of stochastic multi-armed bandits. One of our main results is showing that the Boltzmann exploration strategy with any monotone learning-rate sequence will induce suboptimal behavior. As a remedy, we offer a simple non-monotone schedule that guarantees near-optimal performance, albeit only when given prior access to key problem parameters that are typically not available in practical situations (like the time horizon $T$ and the suboptimality gap $Δ$). More importantly, we propose a novel variant that uses different learning rates for different arms, and achieves a distribution-dependent regret bound of order $\frac{K\log^2 T}Δ$ and a distribution-independent bound of order $\sqrt{KT}\log K$ without requiring such prior knowledge. To demonstrate the flexibility of our technique, we also propose a variant that guarantees the same performance bounds even if the rewards are heavy-tailed.

cs.LG↗

arXiv2017

On the Hardness of Inventory Management with Censored Demand Data

We consider a repeated newsvendor problem where the inventory manager has no prior information about the demand, and can access only censored/sales data. In analogy to multi-armed bandit problems, the manager needs to simultaneously "explore" and "exploit" with her inventory decisions, in order to minimize the cumulative cost. We make no probabilistic assumptions---importantly, independence or time stationarity---regarding the mechanism that creates the demand sequence. Our goal is to shed light on the hardness of the problem, and to develop policies that perform well with respect to the regret criterion, that is, the difference between the cumulative cost of a policy and that of the best fixed action/static inventory decision in hindsight, uniformly over all feasible demand sequences. We show that a simple randomized policy, termed the Exponentially Weighted Forecaster, combined with a carefully designed cost estimator, achieves optimal scaling of the expected regret (up to logarithmic factors) with respect to all three key primitives: the number of time periods, the number of inventory decisions available, and the demand support. Through this result, we derive an important insight: the benefit from "information stalking" as well as the cost of censoring are both negligible in this dynamic learning problem, at least with respect to the regret criterion. Furthermore, we modify the proposed policy in order to perform well in terms of the tracking regret, that is, using as benchmark the best sequence of inventory decisions that switches a limited number of times. Numerical experiments suggest that the proposed approach outperforms existing ones (that are tailored to, or facilitated by, time stationarity) on nonstationary demand models. Finally, we extend the proposed approach and its analysis to a "combinatorial" version of the repeated newsvendor problem.

cs.LG↗

arXiv2017

Algorithmic stability and hypothesis complexity

We introduce a notion of algorithmic stability of learning algorithms---that we term \emph{argument stability}---that captures stability of the hypothesis output by the learning algorithm in the normed space of functions from which hypotheses are selected. The main result of the paper bounds the generalization error of any learning algorithm in terms of its argument stability. The bounds are based on martingale inequalities in the Banach space to which the hypotheses belong. We apply the general bounds to bound the performance of some learning algorithms based on empirical risk minimization and stochastic gradient descent.

stat.ML↗

arXiv2017

An Improved Parametrization and Analysis of the EXP3++ Algorithm for Stochastic and Adversarial Bandits

We present a new strategy for gap estimation in randomized algorithms for multiarmed bandits and combine it with the EXP3++ algorithm of Seldin and Slivkins (2014). In the stochastic regime the strategy reduces dependence of regret on a time horizon from $(\ln t)^3$ to $(\ln t)^2$ and eliminates an additive factor of order $Δe^{1/Δ^2}$, where $Δ$ is the minimal gap of a problem instance. In the adversarial regime regret guarantee remains unchanged.

cs.LG↗

arXiv2017

Sub-Gaussian estimators of the mean of a random vector

We study the problem of estimating the mean of a random vector $X$ given a sample of $N$ independent, identically distributed points. We introduce a new estimator that achieves a purely sub-Gaussian performance under the only condition that the second moment of $X$ exists. The estimator is based on a novel concept of a multivariate median.

math.ST↗

arXiv2016

Detecting a Path of Correlations in a Network

We consider the problem of detecting an anomaly in the form of a path of correlations hidden in white noise. We provide a minimax lower bound and a test that, under mild assumptions, is able to achieve the lower bound up to a multiplicative constant.

math.ST↗

arXiv2016

On the estimation of the mean of a random vector

We study the problem of estimating the mean of a multivariatedistribution based on independent samples. The main result is the proof of existence of an estimator with a non-asymptotic sub-Gaussian performance for all distributions satisfying some mild moment assumptions.

math.ST↗