arXiv subjects

Constantinos Daskalakis

Publications and source records attributed to Constantinos Daskalakis.

At least 73 records · Page 4Linked to original sources

arXiv2021

GANs with Conditional Independence Graphs: On Subadditivity of Probability Divergences

Generative Adversarial Networks (GANs) are modern methods to learn the underlying distribution of a data set. GANs have been widely used in sample synthesis, de-noising, domain transfer, etc. GANs, however, are designed in a model-free fashion where no additional information about the underlying distribution is available. In many applications, however, practitioners have access to the underlying independence graph of the variables, either as a Bayesian network or a Markov Random Field (MRF). We ask: how can one use this additional information in designing model-based GANs? In this paper, we provide theoretical foundations to answer this question by studying subadditivity properties of probability divergences, which establish upper bounds on the distance between two high-dimensional distributions by the sum of distances between their marginals over (local) neighborhoods of the graphical structure of the Bayes-net or the MRF. We prove that several popular probability divergences satisfy some notion of subadditivity under mild conditions. These results lead to a principled design of a model-based GAN that uses a set of simple discriminators on the neighborhoods of the Bayes-net/MRF, rather than a giant discriminator on the entire network, providing significant statistical and computational benefits. Our experiments on synthetic and real-world datasets demonstrate the benefits of our principled design of model-based GANs.

cs.LG↗

arXiv2021

Independent Policy Gradient Methods for Competitive Reinforcement Learning

We obtain global, non-asymptotic convergence guarantees for independent learning algorithms in competitive reinforcement learning settings with two agents (i.e., zero-sum stochastic games). We consider an episodic setting where in each episode, each player independently selects a policy and observes only their own actions and rewards, along with the state. We show that if both players run policy gradient methods in tandem, their policies will converge to a min-max equilibrium of the game, as long as their learning rates follow a two-timescale rule (which is necessary). To the best of our knowledge, this constitutes the first finite-sample convergence result for independent policy gradient methods in competitive RL; prior work has largely focused on centralized, coordinated procedures for equilibrium computation.

cs.LG↗

arXiv2020

Learning Ising models from one or multiple samples

There have been two separate lines of work on estimating Ising models: (1) estimating them from multiple independent samples under minimal assumptions about the model's interaction matrix; and (2) estimating them from one sample in restrictive settings. We propose a unified framework that smoothly interpolates between these two settings, enabling significantly richer estimation guarantees from one, a few, or many samples. Our main theorem provides guarantees for one-sample estimation, quantifying the estimation error in terms of the metric entropy of a family of interaction matrices. As corollaries of our main theorem, we derive bounds when the model's interaction matrix is a (sparse) linear combination of known matrices, or it belongs to a finite set, or to a high-dimensional manifold. In fact, our main result handles multiple independent samples by viewing them as one sample from a larger model, and can be used to derive estimation bounds that are qualitatively similar to those obtained in the afore-described multiple-sample literature. Our technical approach benefits from sparsifying a model's interaction network, conditioning on subsets of variables that make the dependencies in the resulting conditional distribution sufficiently weak. We use this sparsification technique to prove strong concentration and anti-concentration results for the Ising model, which we believe have applications beyond the scope of this paper.

math.ST↗

arXiv2020

Sample-Optimal and Efficient Learning of Tree Ising models

We show that $n$-variable tree-structured Ising models can be learned computationally-efficiently to within total variation distance $ε$ from an optimal $O(n \ln n/ε^2)$ samples, where $O(\cdot)$ hides an absolute constant which, importantly, does not depend on the model being learned - neither its tree nor the magnitude of its edge strengths, on which we place no assumptions. Our guarantees hold, in fact, for the celebrated Chow-Liu [1968] algorithm, using the plug-in estimator for estimating mutual information. While this (or any other) algorithm may fail to identify the structure of the underlying model correctly from a finite sample, we show that it will still learn a tree-structured model that is $ε$-close to the true one in total variation distance, a guarantee called "proper learning." Our guarantees do not follow from known results for the Chow-Liu algorithm and the ensuing literature on learning graphical models, including a recent renaissance of algorithms on this learning challenge, which only yield asymptotic consistency results, or sample-inefficient and/or time-inefficient algorithms, unless further assumptions are placed on the graphical model, such as bounds on the "strengths" of the model's edges/hyperedges. While we establish guarantees for a widely known and simple algorithm, the analysis that this algorithm succeeds and is sample-optimal is quite complex, requiring a hierarchical classification of the edges into layers with different reconstruction guarantees, depending on their strength, combined with delicate uses of the subadditivity of the squared Hellinger distance over graphical models to control the error accumulation.

cs.LG↗

arXiv2020

Tight last-iterate convergence rates for no-regret learning in multi-player games

We study the question of obtaining last-iterate convergence rates for no-regret learning algorithms in multi-player games. We show that the optimistic gradient (OG) algorithm with a constant step-size, which is no-regret, achieves a last-iterate rate of $O(1/\sqrt{T})$ with respect to the gap function in smooth monotone games. This result addresses a question of Mertikopoulos & Zhou (2018), who asked whether extra-gradient approaches (such as OG) can be applied to achieve improved guarantees in the multi-agent learning setting. The proof of our upper bound uses a new technique centered around an adaptive choice of potential function at each iteration. We also show that the $O(1/\sqrt{T})$ rate is tight for all $p$-SCLI algorithms, which includes OG as a special case. As a byproduct of our lower bound analysis we additionally present a proof of a conjecture of Arjevani et al. (2015) which is more direct than previous approaches.

cs.LG↗

arXiv2020

Efficient Statistics, in High Dimensions, from Truncated Samples

We provide an efficient algorithm for the classical problem, going back to Galton, Pearson, and Fisher, of estimating, with arbitrary accuracy the parameters of a multivariate normal distribution from truncated samples. Truncated samples from a $d$-variate normal ${\cal N}(\mathbfμ,\mathbfΣ)$ means a samples is only revealed if it falls in some subset $S \subseteq \mathbb{R}^d$; otherwise the samples are hidden and their count in proportion to the revealed samples is also hidden. We show that the mean $\mathbfμ$ and covariance matrix $\mathbfΣ$ can be estimated with arbitrary accuracy in polynomial-time, as long as we have oracle access to $S$, and $S$ has non-trivial measure under the unknown $d$-variate normal distribution. Additionally we show that without oracle access to $S$, any non-trivial estimation is impossible.

math.ST↗

arXiv2020

Computationally and Statistically Efficient Truncated Regression

We provide a computationally and statistically efficient estimator for the classical problem of truncated linear regression, where the dependent variable $y = w^T x + ε$ and its corresponding vector of covariates $x \in R^k$ are only revealed if the dependent variable falls in some subset $S \subseteq R$; otherwise the existence of the pair $(x, y)$ is hidden. This problem has remained a challenge since the early works of [Tobin 1958, Amemiya 1973, Hausman and Wise 1977], its applications are abundant, and its history dates back even further to the work of Galton, Pearson, Lee, and Fisher. While consistent estimators of the regression coefficients have been identified, the error rates are not well-understood, especially in high dimensions. Under a thickness assumption about the covariance matrix of the covariates in the revealed sample, we provide a computationally efficient estimator for the coefficient vector $w$ from $n$ revealed samples that attains $l_2$ error $\tilde{O}(\sqrt{k/n})$. Our estimator uses Projected Stochastic Gradient Descent (PSGD) without replacement on the negative log-likelihood of the truncated sample. For the statistically efficient estimation we only need oracle access to the set $S$.In order to achieve computational efficiency we need to assume that $S$ is a union of a finite number of intervals but still can be complicated. PSGD without replacement must be restricted to an appropriately defined convex cone to guarantee that the negative log-likelihood is strongly convex, which in turn is established using concentration of matrices on variables with sub-exponential tails. We perform experiments on simulated data to illustrate the accuracy of our estimator. As a corollary, we show that SGD learns the parameters of single-layer neural networks with noisy activation functions.

math.ST↗

arXiv2020

The Complexity of Constrained Min-Max Optimization

Despite its important applications in Machine Learning, min-max optimization of nonconvex-nonconcave objectives remains elusive. Not only are there no known first-order methods converging even to approximate local min-max points, but the computational complexity of identifying them is also poorly understood. In this paper, we provide a characterization of the computational complexity of the problem, as well as of the limitations of first-order methods in constrained min-max optimization problems with nonconvex-nonconcave objectives and linear constraints. As a warm-up, we show that, even when the objective is a Lipschitz and smooth differentiable function, deciding whether a min-max point exists, in fact even deciding whether an approximate min-max point exists, is NP-hard. More importantly, we show that an approximate local min-max point of large enough approximation is guaranteed to exist, but finding one such point is PPAD-complete. The same is true of computing an approximate fixed point of Gradient Descent/Ascent. An important byproduct of our proof is to establish an unconditional hardness result in the Nemirovsky-Yudin model. We show that, given oracle access to some function $f : P \to [-1, 1]$ and its gradient $\nabla f$, where $P \subseteq [0, 1]^d$ is a known convex polytope, every algorithm that finds a $\varepsilon$-approximate local min-max point needs to make a number of queries that is exponential in at least one of $1/\varepsilon$, $L$, $G$, or $d$, where $L$ and $G$ are respectively the smoothness and Lipschitzness of $f$ and $d$ is the dimension. This comes in sharp contrast to minimization problems, where finding approximate local minima in the same setting can be done with Projected Gradient Descent using $O(L/\varepsilon)$ many queries. Our result is the first to show an exponential separation between these two fundamental optimization problems.

cs.CC↗

arXiv2020

Truncated Linear Regression in High Dimensions

As in standard linear regression, in truncated linear regression, we are given access to observations $(A_i, y_i)_i$ whose dependent variable equals $y_i= A_i^{\rm T} \cdot x^* + η_i$, where $x^*$ is some fixed unknown vector of interest and $η_i$ is independent noise; except we are only given an observation if its dependent variable $y_i$ lies in some "truncation set" $S \subset \mathbb{R}$. The goal is to recover $x^*$ under some favorable conditions on the $A_i$'s and the noise distribution. We prove that there exists a computationally and statistically efficient method for recovering $k$-sparse $n$-dimensional vectors $x^*$ from $m$ truncated samples, which attains an optimal $\ell_2$ reconstruction error of $O(\sqrt{(k \log n)/m})$. As a corollary, our guarantees imply a computationally efficient and information-theoretically optimal algorithm for compressed sensing with truncation, which may arise from measurement saturation effects. Our result follows from a statistical and computational analysis of the Stochastic Gradient Descent (SGD) algorithm for solving a natural adaptation of the LASSO optimization problem that accommodates truncation. This generalizes the works of both: (1) [Daskalakis et al. 2018], where no regularization is needed due to the low-dimensionality of the data, and (2) [Wainright 2009], where the objective function is simple due to the absence of truncation. In order to deal with both truncation and high-dimensionality at the same time, we develop new techniques that not only generalize the existing ones but we believe are of independent interest.

cs.LG↗

arXiv2020

Last Iterate is Slower than Averaged Iterate in Smooth Convex-Concave Saddle Point Problems

In this paper we study the smooth convex-concave saddle point problem. Specifically, we analyze the last iterate convergence properties of the Extragradient (EG) algorithm. It is well known that the ergodic (averaged) iterates of EG converge at a rate of $O(1/T)$ (Nemirovski, 2004). In this paper, we show that the last iterate of EG converges at a rate of $O(1/\sqrt{T})$. To the best of our knowledge, this is the first paper to provide a convergence rate guarantee for the last iterate of EG for the smooth convex-concave saddle point problem. Moreover, we show that this rate is tight by proving a lower bound of $Ω(1/\sqrt{T})$ for the last iterate. This lower bound therefore shows a quadratic separation of the convergence rates of ergodic and last iterates in smooth convex-concave saddle point problems.

cs.LG↗

arXiv2020

SGD Learns One-Layer Networks in WGANs

Generative adversarial networks (GANs) are a widely used framework for learning generative models. Wasserstein GANs (WGANs), one of the most successful variants of GANs, require solving a minmax optimization problem to global optimality, but are in practice successfully trained using stochastic gradient descent-ascent. In this paper, we show that, when the generator is a one-layer network, stochastic gradient descent-ascent converges to a global solution with polynomial time and sample complexity.

cs.LG↗

arXiv2020

Constant-Expansion Suffices for Compressed Sensing with Generative Priors

Generative neural networks have been empirically found very promising in providing effective structural priors for compressed sensing, since they can be trained to span low-dimensional data manifolds in high-dimensional signal spaces. Despite the non-convexity of the resulting optimization problem, it has also been shown theoretically that, for neural networks with random Gaussian weights, a signal in the range of the network can be efficiently, approximately recovered from a few noisy measurements. However, a major bottleneck of these theoretical guarantees is a network expansivity condition: that each layer of the neural network must be larger than the previous by a logarithmic factor. Our main contribution is to break this strong expansivity assumption, showing that constant expansivity suffices to get efficient recovery algorithms, besides it also being information-theoretically necessary. To overcome the theoretical bottleneck in existing approaches we prove a novel uniform concentration theorem for random functions that might not be Lipschitz but satisfy a relaxed notion which we call "pseudo-Lipschitzness." Using this theorem we can show that a matrix concentration inequality known as the Weight Distribution Condition (WDC), which was previously only known to hold for Gaussian matrices with logarithmic aspect ratio, in fact holds for constant aspect ratios too. Since the WDC is a fundamental matrix concentration inequality in the heart of all existing theoretical guarantees on this problem, our tighter bound immediately yields improvements in all known results in the literature on compressed sensing with deep generative priors, including one-bit recovery, phase retrieval, low-rank matrix recovery, and more.

cs.IT↗

arXiv2020

Multi-Item Mechanisms without Item-Independence: Learnability via Robustness

We study the sample complexity of learning revenue-optimal multi-item auctions. We obtain the first set of positive results that go beyond the standard but unrealistic setting of item-independence. In particular, we consider settings where bidders' valuations are drawn from correlated distributions that can be captured by Markov Random Fields or Bayesian Networks -- two of the most prominent graphical models. We establish parametrized sample complexity bounds for learning an up-to-$\varepsilon$ optimal mechanism in both models, which scale polynomially in the size of the model, i.e.~the number of items and bidders, and only exponential in the natural complexity measure of the model, namely either the largest in-degree (for Bayesian Networks) or the size of the largest hyper-edge (for Markov Random Fields). We obtain our learnability results through a novel and modular framework that involves first proving a robustness theorem. We show that, given only ``approximate distributions'' for bidder valuations, we can learn a mechanism whose revenue is nearly optimal simultaneously for all ``true distributions'' that are close to the ones we were given in Prokhorov distance. Thus, to learn a good mechanism, it suffices to learn approximate distributions. When item values are independent, learning in Prokhorov distance is immediate, hence our framework directly implies the main result of Gonczarowski and Weinberg. When item values are sampled from more general graphical models, we combine our robustness theorem with novel sample complexity results for learning Markov Random Fields or Bayesian Networks in Prokhorov distance, which may be of independent interest. Finally, in the single-item case, our robustness result can be strengthened to hold under an even weaker distribution distance, the Lévy distance.

cs.GT↗

arXiv2020

Logistic-Regression with peer-group effects via inference in higher order Ising models

Spin glass models, such as the Sherrington-Kirkpatrick, Hopfield and Ising models, are all well-studied members of the exponential family of discrete distributions, and have been influential in a number of application domains where they are used to model correlation phenomena on networks. Conventionally these models have quadratic sufficient statistics and consequently capture correlations arising from pairwise interactions. In this work we study extensions of these to models with higher-order sufficient statistics, modeling behavior on a social network with peer-group effects. In particular, we model binary outcomes on a network as a higher-order spin glass, where the behavior of an individual depends on a linear function of their own vector of covariates and some polynomial function of the behavior of others, capturing peer-group effects. Using a {\em single}, high-dimensional sample from such model our goal is to recover the coefficients of the linear function as well as the strength of the peer-group effects. The heart of our result is a novel approach for showing strong concavity of the log pseudo-likelihood of the model, implying statistical error rate of $\sqrt{d/n}$ for the Maximum Pseudo-Likelihood Estimator (MPLE), where $d$ is the dimensionality of the covariate vectors and $n$ is the size of the network (number of nodes). Our model generalizes vanilla logistic regression as well as the peer-effect models studied in recent works, and our results extend these results to accommodate higher-order interactions.

stat.ML↗

arXiv2019

Regression from Dependent Observations

The standard linear and logistic regression models assume that the response variables are independent, but share the same linear relationship to their corresponding vectors of covariates. The assumption that the response variables are independent is, however, too strong. In many applications, these responses are collected on nodes of a network, or some spatial or temporal domain, and are dependent. Examples abound in financial and meteorological applications, and dependencies naturally arise in social networks through peer effects. Regression with dependent responses has thus received a lot of attention in the Statistics and Economics literature, but there are no strong consistency results unless multiple independent samples of the vectors of dependent responses can be collected from these models. We present computationally and statistically efficient methods for linear and logistic regression models when the response variables are dependent on a network. Given one sample from a networked linear or logistic regression model and under mild assumptions, we prove strong consistency results for recovering the vector of coefficients and the strength of the dependencies, recovering the rates of standard regression under independent observations. We use projected gradient descent on the negative log-likelihood, or negative log-pseudolikelihood, and establish their strong convexity and consistency using concentration of measure for dependent random variables.

cs.LG↗

arXiv2019

Testing Ising Models

Given samples from an unknown multivariate distribution $p$, is it possible to distinguish whether $p$ is the product of its marginals versus $p$ being far from every product distribution? Similarly, is it possible to distinguish whether $p$ equals a given distribution $q$ versus $p$ and $q$ being far from each other? These problems of testing independence and goodness-of-fit have received enormous attention in statistics, information theory, and theoretical computer science, with sample-optimal algorithms known in several interesting regimes of parameters. Unfortunately, it has also been understood that these problems become intractable in large dimensions, necessitating exponential sample complexity. Motivated by the exponential lower bounds for general distributions as well as the ubiquity of Markov Random Fields (MRFs) in the modeling of high-dimensional distributions, we initiate the study of distribution testing on structured multivariate distributions, and in particular the prototypical example of MRFs: the Ising Model. We demonstrate that, in this structured setting, we can avoid the curse of dimensionality, obtaining sample and time efficient testers for independence and goodness-of-fit. One of the key technical challenges we face along the way is bounding the variance of functions of the Ising model.

cs.DS↗

arXiv2019

The Robust Manifold Defense: Adversarial Training using Generative Models

We propose a new type of attack for finding adversarial examples for image classifiers. Our method exploits spanners, i.e. deep neural networks whose input space is low-dimensional and whose output range approximates the set of images of interest. Spanners may be generators of GANs or decoders of VAEs. The key idea in our attack is to search over latent code pairs to find ones that generate nearby images with different classifier outputs. We argue that our attack is stronger than searching over perturbations of real images. Moreover, we show that our stronger attack can be used to reduce the accuracy of Defense-GAN to 3\%, resolving an open problem from the well-known paper by Athalye et al. We combine our attack with normal adversarial training to obtain the most robust known MNIST classifier, significantly improving the state of the art against PGD attacks. Our formulation involves solving a min-max problem, where the min player sets the parameters of the classifier and the max player is running our attack, and is thus searching for adversarial examples in the {\em low-dimensional} input space of the spanner. All code and models are available at \url{https://github.com/ajiljalal/manifold-defense.git}

cs.CV↗

arXiv2019

Learning from weakly dependent data under Dobrushin's condition

Statistical learning theory has largely focused on learning and generalization given independent and identically distributed (i.i.d.) samples. Motivated by applications involving time-series data, there has been a growing literature on learning and generalization in settings where data is sampled from an ergodic process. This work has also developed complexity measures, which appropriately extend the notion of Rademacher complexity to bound the generalization error and learning rates of hypothesis classes in this setting. Rather than time-series data, our work is motivated by settings where data is sampled on a network or a spatial domain, and thus do not fit well within the framework of prior work. We provide learning and generalization bounds for data that are complexly dependent, yet their distribution satisfies the standard Dobrushin's condition. Indeed, we show that the standard complexity measures of Gaussian and Rademacher complexities and VC dimension are sufficient measures of complexity for the purposes of bounding the generalization error and learning rates of hypothesis classes in our setting. Moreover, our generalization bounds only degrade by constant factors compared to their i.i.d. analogs, and our learnability bounds degrade by log factors in the size of the training set.

cs.LG↗