Collaborating Authors Machine Learning

Causal Inference Under Unmeasured Confounding With Negative Controls: A Minimax Learning Approach Machine Learning

We study the estimation of causal parameters when not all confounders are observed and instead negative controls are available. Recent work has shown how these can enable identification and efficient estimation via two so-called bridge functions. In this paper, we tackle the primary challenge to causal inference using negative controls: the identification and estimation of these bridge functions. Previous work has relied on uniqueness and completeness assumptions on these functions that may be implausible in practice and also focused on their parametric estimation. Instead, we provide a new identification strategy that avoids both uniqueness and completeness. And, we provide a new estimators for these functions based on minimax learning formulations. These estimators accommodate general function classes such as reproducing Hilbert spaces and neural networks. We study finite-sample convergence results both for estimating bridge function themselves and for the final estimation of the causal parameter. We do this under a variety of combinations of assumptions that include realizability and closedness conditions on the hypothesis and critic classes employed in the minimax estimator. Depending on how much we are willing to assume, we obtain different convergence rates. In some cases, we show the estimate for the causal parameter may converge even when our bridge function estimators do not converge to any valid bridge function. And, in other cases, we show we can obtain semiparametric efficiency.

Multinomial Logit Contextual Bandits: Provable Optimality and Practicality Machine Learning

We consider a sequential assortment selection problem where the user choice is given by a multinomial logit (MNL) choice model whose parameters are unknown. In each period, the learning agent observes a $d$-dimensional contextual information about the user and the $N$ available items, and offers an assortment of size $K$ to the user, and observes the bandit feedback of the item chosen from the assortment. We propose upper confidence bound based algorithms for this MNL contextual bandit. The first algorithm is a simple and practical method which achieves an $\tilde{\mathcal{O}}(d\sqrt{T})$ regret over $T$ rounds. Next, we propose a second algorithm which achieves a $\tilde{\mathcal{O}}(\sqrt{dT})$ regret. This matches the lower bound for the MNL bandit problem, up to logarithmic terms, and improves on the best known result by a $\sqrt{d}$ factor. To establish this sharper regret bound, we present a non-asymptotic confidence bound for the maximum likelihood estimator of the MNL model that may be of independent interest as its own theoretical contribution. We then revisit the simpler, significantly more practical, first algorithm and show that a simple variant of the algorithm achieves the optimal regret for a broad class of important applications.

Interpretable Approximation of High-Dimensional Data Machine Learning

In this paper we apply the previously introduced approximation method based on the ANOVA (analysis of variance) decomposition and Grouped Transformations to synthetic and real data. The advantage of this method is the interpretability of the approximation, i.e., the ability to rank the importance of the attribute interactions or the variable couplings. Moreover, we are able to generate an attribute ranking to identify unimportant variables and reduce the dimensionality of the problem. We compare the method to other approaches on publicly available benchmark datasets.

Neural Architecture Search From Fr\'echet Task Distance Machine Learning

We formulate a Fr\'echet-type asymmetric distance between tasks based on Fisher Information Matrices. We show how the distance between a target task and each task in a given set of baseline tasks can be used to reduce the neural architecture search space for the target task. The complexity reduction in search space for task-specific architectures is achieved by building on the optimized architectures for similar tasks instead of doing a full search without using this side information. Experimental results demonstrate the efficacy of the proposed approach and its improvements over the state-of-the-art methods.

Data Generation in Low Sample Size Setting Using Manifold Sampling and a Geometry-Aware VAE Machine Learning

While much efforts have been focused on improving Variational Autoencoders through richer posterior and prior distributions, little interest was shown in amending the way we generate the data. In this paper, we develop two non \emph{prior-dependent} generation procedures based on the geometry of the latent space seen as a Riemannian manifold. The first one consists in sampling along geodesic paths which is a natural way to explore the latent space while the second one consists in sampling from the inverse of the metric volume element which is easier to use in practice. Both methods are then compared to \emph{prior-based} methods on various data sets and appear well suited for a limited data regime. Finally, the latter method is used to perform data augmentation in a small sample size setting and is validated across various standard and \emph{real-life} data sets. In particular, this scheme allows to greatly improve classification results on the OASIS database where balanced accuracy jumps from 80.7% for a classifier trained with the raw data to 89.1% when trained only with the synthetic data generated by our method. Such results were also observed on 4 standard data sets.

Inductive Mutual Information Estimation: A Convex Maximum-Entropy Copula Approach Machine Learning

We propose a novel estimator of the mutual information between two ordinal vectors $x$ and $y$. Our approach is inductive (as opposed to deductive) in that it depends on the data generating distribution solely through some nonparametric properties revealing associations in the data, and does not require having enough data to fully characterize the true joint distributions $P_{x, y}$. Specifically, our approach consists of (i) noting that $I\left(y; x\right) = I\left(u_y; u_x\right)$ where $u_y$ and $u_x$ are the copula-uniform dual representations of $y$ and $x$ (i.e. their images under the probability integral transform), and (ii) estimating the copula entropies $h\left(u_y\right)$, $h\left(u_x\right)$ and $h\left(u_y, u_x\right)$ by solving a maximum-entropy problem over the space of copula densities under a constraint of the type $\alpha_m = E\left[\phi_m(u_y, u_x)\right]$. We prove that, so long as the constraint is feasible, this problem admits a unique solution, it is in the exponential family, and it can be learned by solving a convex optimization problem. The resulting estimator, which we denote MIND, is marginal-invariant, always non-negative, unbounded for any sample size $n$, consistent, has MSE rate $O(1/n)$, and is more data-efficient than competing approaches. Beyond mutual information estimation, we illustrate that our approach may be used to mitigate mode collapse in GANs by maximizing the entropy of the copula of fake samples, a model we refer to as Copula Entropy Regularized GAN (CER-GAN).

Solving Inverse Problems by Joint Posterior Maximization with Autoencoding Prior Machine Learning

In this work we address the problem of solving ill-posed inverse problems in imaging where the prior is a variational autoencoder (VAE). Specifically we consider the decoupled case where the prior is trained once and can be reused for many different log-concave degradation models without retraining. Whereas previous MAP-based approaches to this problem lead to highly non-convex optimization algorithms, our approach computes the joint (space-latent) MAP that naturally leads to alternate optimization algorithms and to the use of a stochastic encoder to accelerate computations. The resulting technique (JPMAP) performs Joint Posterior Maximization using an Autoencoding Prior. We show theoretical and experimental evidence that the proposed objective function is quite close to bi-convex. Indeed it satisfies a weak bi-convexity property which is sufficient to guarantee that our optimization scheme converges to a stationary point. We also highlight the importance of correctly training the VAE using a denoising criterion, in order to ensure that the encoder generalizes well to out-of-distribution images, without affecting the quality of the generative model. This simple modification is key to providing robustness to the whole procedure. Finally we show how our joint MAP methodology relates to more common MAP approaches, and we propose a continuation scheme that makes use of our JPMAP algorithm to provide more robust MAP estimates. Experimental results also show the higher quality of the solutions obtained by our JPMAP approach with respect to other non-convex MAP approaches which more often get stuck in spurious local optima.

Conditions and Assumptions for Constraint-based Causal Structure Learning Machine Learning

The paper formalizes constraint-based structure learning of the "true" causal graph from observed data when unobserved variables are also existent. We define a "generic" structure learning algorithm, which provides conditions that, under the faithfulness assumption, the output of all known exact algorithms in the literature must satisfy, and which outputs graphs that are Markov equivalent to the causal graph. More importantly, we provide clear assumptions, weaker than faithfulness, under which the same generic algorithm outputs Markov equivalent graphs to the causal graph. We provide the theory for the general class of models under the assumption that the distribution is Markovian to the true causal graph, and we specialize the definitions and results for structural causal models.

Recovery of Joint Probability Distribution from one-way marginals: Low rank Tensors and Random Projections Machine Learning

Joint probability mass function (PMF) estimation is a fundamental machine learning problem. The number of free parameters scales exponentially with respect to the number of random variables. Hence, most work on nonparametric PMF estimation is based on some structural assumptions such as clique factorization adopted by probabilistic graphical models, imposition of low rank on the joint probability tensor and reconstruction from 3-way or 2-way marginals, etc. In the present work, we link random projections of data to the problem of PMF estimation using ideas from tomography. We integrate this idea with the idea of low-rank tensor decomposition to show that we can estimate the joint density from just one-way marginals in a transformed space. We provide a novel algorithm for recovering factors of the tensor from one-way marginals, test it across a variety of synthetic and real-world datasets, and also perform MAP inference on the estimated model for classification.

Debiased Kernel Methods Machine Learning

I propose a practical procedure based on bias correction and sample splitting to calculate confidence intervals for functionals of generic kernel methods, i.e. nonparametric estimators learned in a reproducing kernel Hilbert space (RKHS). For example, an analyst may desire confidence intervals for functionals of kernel ridge regression. I propose a bias correction that mirrors kernel ridge regression. The framework encompasses (i) evaluations over discrete domains, (ii) derivatives over continuous domains, (iii) treatment effects of discrete treatments, and (iv) incremental treatment effects of continuous treatments. For the target quantity, whether it is (i)-(iv), I prove root-n consistency, Gaussian approximation, and semiparametric efficiency by finite sample arguments. I show that the classic assumptions of RKHS learning theory also imply inference.