This paper proposes simple, data-driven, optimal rate-adaptive inferences on a structural function in semi-nonparametric conditional moment restrictions. We consider two types of hypothesis tests based on leave-one-out sieve estimators. A structure-space test (ST) uses a quadratic distance between the structural functions of endogenous variables; while an image-space test (IT) uses a quadratic distance of the conditional moment from zero. For both tests, we analyze their respective classes of nonparametric alternative models that are separated from the null hypothesis by the minimax rate of testing. That is, the sum of the type I and the type II errors of the test, uniformly over the class of nonparametric alternative models, cannot be improved by any other test. Our new minimax rate of ST differs from the known minimax rate of estimation in nonparametric instrumental variables (NPIV) models. We propose computationally simple and novel exponential scan data-driven choices of sieve regularization parameters and adjusted chi-squared critical values. The resulting tests attain the minimax rate of testing, and hence optimally adapt to the unknown smoothness of functions and are robust to the unknown degree of ill-posedness (endogeneity). Data-driven confidence sets are easily obtained by inverting the adaptive ST. Monte Carlo studies demonstrate that our adaptive ST has good size and power properties in finite samples for testing monotonicity or equality restrictions in NPIV models. Empirical applications to nonparametric multi-product demands with endogenous prices are presented.

We study the problem of least squares linear regression where the data-points are dependent and are sampled from a Markov chain. We establish sharp information theoretic minimax lower bounds for this problem in terms of $\tau_{\mathsf{mix}}$, the mixing time of the underlying Markov chain, under different noise settings. Our results establish that in general, optimization with Markovian data is strictly harder than optimization with independent data and a trivial algorithm (SGD-DD) that works with only one in every $\tilde{\Theta}(\tau_{\mathsf{mix}})$ samples, which are approximately independent, is minimax optimal. In fact, it is strictly better than the popular Stochastic Gradient Descent (SGD) method with constant step-size which is otherwise minimax optimal in the regression with independent data setting. Beyond a worst case analysis, we investigate whether structured datasets seen in practice such as Gaussian auto-regressive dynamics can admit more efficient optimization schemes. Surprisingly, even in this specific and natural setting, Stochastic Gradient Descent (SGD) with constant step-size is still no better than SGD-DD. Instead, we propose an algorithm based on experience replay--a popular reinforcement learning technique--that achieves a significantly better error rate. Our improved rate serves as one of the first results where an algorithm outperforms SGD-DD on an interesting Markov chain and also provides one of the first theoretical analyses to support the use of experience replay in practice.

Behavioral cues play a significant part in human communication and cognitive perception. In most professional domains, employee recruitment policies are framed such that both professional skills and personality traits are adequately assessed. Hiring interviews are structured to evaluate expansively a potential employee's suitability for the position - their professional qualifications, interpersonal skills, ability to perform in critical and stressful situations, in the presence of time and resource constraints, etc. Therefore, candidates need to be aware of their positive and negative attributes and be mindful of behavioral cues that might have adverse effects on their success. We propose a multimodal analytical framework that analyzes the candidate in an interview scenario and provides feedback for predefined labels such as engagement, speaking rate, eye contact, etc. We perform a comprehensive analysis that includes the interviewee's facial expressions, speech, and prosodic information, using the video, audio, and text transcripts obtained from the recorded interview. We use these multimodal data sources to construct a composite representation, which is used for training machine learning classifiers to predict the class labels. Such analysis is then used to provide constructive feedback to the interviewee for their behavioral cues and body language. Experimental validation showed that the proposed methodology achieved promising results.

The true population-level importance of a variable in a prediction task provides useful knowledge about the underlying data-generating mechanism and can help in deciding which measurements to collect in subsequent experiments. Valid statistical inference on this importance is a key component in understanding the population of interest. We present a computationally efficient procedure for estimating and obtaining valid statistical inference on the Shapley Population Variable Importance Measure (SPVIM). Although the computational complexity of the true SPVIM scales exponentially with the number of variables, we propose an estimator based on randomly sampling only $\Theta(n)$ feature subsets given $n$ observations. We prove that our estimator converges at an asymptotically optimal rate. Moreover, by deriving the asymptotic distribution of our estimator, we construct valid confidence intervals and hypothesis tests. Our procedure has good finite-sample performance in simulations, and for an in-hospital mortality prediction task produces similar variable importance estimates when different machine learning algorithms are applied.

Consider the problem of learning a large number of response functions simultaneously based on the same input variables. The training data consist of a single independent random sample of the input variables drawn from a common distribution together with the associated responses. The input variables are mapped into a high-dimensional linear space, called the feature space, and the response functions are modelled as linear functionals of the mapped features, with coefficients calibrated via ordinary least squares. We provide convergence guarantees on the worst-case excess prediction risk by controlling the convergence rate of the excess risk uniformly in the response function. The dimension of the feature map is allowed to tend to infinity with the sample size. The collection of response functions, although potentiallyinfinite, is supposed to have a finite Vapnik-Chervonenkis dimension. The bound derived can be applied when building multiple surrogate models in a reasonable computing time.

Zero-shot object recognition or zero-shot learning aims to transfer the object recognition ability among the semantically related categories, such as fine-grained animal or bird species. However, the images of different fine-grained objects tend to merely exhibit subtle differences in appearance, which will severely deteriorate zero-shot object recognition. To reduce the superfluous information in the fine-grained objects, in this paper, we propose to learn the redundancy-free features for generalized zero-shot learning. We achieve our motivation by projecting the original visual features into a new (redundancy-free) feature space and then restricting the statistical dependence between these two feature spaces. Furthermore, we require the projected features to keep and even strengthen the category relationship in the redundancy-free feature space. In this way, we can remove the redundant information from the visual features without losing the discriminative information. We extensively evaluate the performance on four benchmark datasets. The results show that our redundancy-free feature based generalized zero-shot learning (RFF-GZSL) approach can outperform the state-of-the-arts often by a large margin. Our code is available.

We present a novel approach to image restoration that leverages ideas from localized structured prediction and non-linear multi-task learning. We optimize a penalized energy function regularized by a sum of terms measuring the distance between patches to be restored and clean patches from an external database gathered beforehand. The resulting estimator comes with strong statistical guarantees leveraging local dependency properties of overlapping patches. We derive the corresponding algorithms for energies based on the mean-squared and Euclidean norm errors. Finally, we demonstrate the practical effectiveness of our model on different image restoration problems using standard benchmarks.

Hierarchical time series demands exist in many industries and are often associated with the product, time frame, or geographic aggregations. Traditionally, these hierarchies have been forecasted using top-down, bottom-up, or middle-out approaches. The question we aim to answer is how to utilize child-level forecasts to improve parent-level forecasts in a hierarchical supply chain. Improved forecasts can be used to considerably reduce logistics costs, especially in e-commerce. We propose a novel multi-phase hierarchical (MPH) approach. Our method involves forecasting each series in the hierarchy independently using machine learning models, then combining all forecasts to allow a second phase model estimation at the parent level. Sales data from MonarchFx Inc. (a logistics solutions provider) is used to evaluate our approach and compare it to bottom-up and top-down methods. Our results demonstrate an 82-90% improvement in forecast accuracy using the proposed approach. Using the proposed method, supply chain planners can derive more accurate forecasting models to exploit the benefit of multivariate data.

We propose an approach to estimate the effect of multiple simultaneous interventions in the presence of hidden confounders. To overcome the problem of hidden confounding, we consider the setting where we have access to not only the observational data but also sets of single-variable interventions in which each of the treatment variables is intervened on separately. We prove identifiability under the assumption that the data is generated from a nonlinear continuous structural causal model with additive Gaussian noise. In addition, we propose a simple parameter estimation method by pooling all the data from different regimes and jointly maximizing the combined likelihood. We also conduct comprehensive experiments to verify the identifiability result as well as to compare the performance of our approach against a baseline on both synthetic and real-world data.

Model fitting often aims to fit a single model, assuming that the imposed form of the model is correct. However, there may be multiple possible underlying explanatory patterns in a set of predictors that could explain a response. Model selection without regarding model uncertainty can fail to bring these patterns to light. We present multi-model penalized regression (MMPR) to acknowledge model uncertainty in the context of penalized regression. In the penalty form introduced here, we explore how different settings can promote either shrinkage or sparsity of coefficients in separate models. A choice of penalty form that enforces variable selection is applied to predict stacking force energy (SFE) from steel alloy composition. The aim is to identify multiple models with different subsets of covariates that explain a single type of response.