The usual Minimum Covariance Determinant (MCD) estimator of a covariance matrix is robust against casewise outliers. These are cases (that is, rows of the data matrix) that behave differently from the majority of cases, raising suspicion that they might belong to a different population. On the other hand, cellwise outliers are individual cells in the data matrix. When a row contains one or more outlying cells, the other cells in the same row still contain useful information that we wish to preserve. We propose a cellwise robust version of the MCD method, called cellMCD. Its main building blocks are observed likelihood and a penalty term on the number of flagged cellwise outliers. It possesses good breakdown properties. We construct a fast algorithm for cellMCD based on concentration steps (C-steps) that always lower the objective. The method performs well in simulations with cellwise outliers, and has high finite-sample efficiency on clean data. It is illustrated on real data with visualizations of the results.

We present sparse tree-based and list-based density estimation methods for binary/categorical data. Our density estimation models are higher dimensional analogies to variable bin width histograms. In each leaf of the tree (or list), the density is constant, similar to the flat density within the bin of a histogram. Histograms, however, cannot easily be visualized in more than two dimensions, whereas our models can. The accuracy of histograms fades as dimensions increase, whereas our models have priors that help with generalization. Our models are sparse, unlike high-dimensional fixed-bin histograms. We present three generative modeling methods, where the first one allows the user to specify the preferred number of leaves in the tree within a Bayesian prior. The second method allows the user to specify the preferred number of branches within the prior. The third method returns density lists (rather than trees) and allows the user to specify the preferred number of rules and the length of rules within the prior. The new approaches often yield a better balance between sparsity and accuracy of density estimates than other methods for this task. We present an application to crime analysis, where we estimate how unusual each type of modus operandi is for a house break-in.

By composing graphical models with deep learning architectures, we learn generative models with the strengths of both frameworks. The structured variational autoencoder (SVAE) inherits structure and interpretability from graphical models, and flexible likelihoods for high-dimensional data from deep learning, but poses substantial optimization challenges. We propose novel algorithms for learning SVAEs, and are the first to demonstrate the SVAE's ability to handle multimodal uncertainty when data is missing by incorporating discrete latent variables. Our memory-efficient implicit differentiation scheme makes the SVAE tractable to learn via gradient descent, while demonstrating robustness to incomplete optimization. To more rapidly learn accurate graphical model parameters, we derive a method for computing natural gradients without manual derivations, which avoids biases found in prior work. These optimization innovations enable the first comparisons of the SVAE to state-of-the-art time series models, where the SVAE performs competitively while learning interpretable and structured discrete data representations.

Fingerprint-based localization improves the positioning performance in challenging, non-line-of-sight (NLoS) dominated indoor environments. However, fingerprinting models require an expensive life-cycle management including recording and labeling of radio signals for the initial training and regularly at environmental changes. Alternatively, channel-charting avoids this labeling effort as it implicitly associates relative coordinates to the recorded radio signals. Then, with reference real-world coordinates (positions) we can use such charts for positioning tasks. However, current channel-charting approaches lag behind fingerprinting in their positioning accuracy and still require reference samples for localization, regular data recording and labeling to keep the models up to date. Hence, we propose a novel framework that does not require reference positions. We only require information from velocity information, e.g., from pedestrian dead reckoning or odometry to model the channel charts, and topological map information, e.g., a building floor plan, to transform the channel charts into real coordinates. We evaluate our approach on two different real-world datasets using 5G and distributed single-input/multiple-output system (SIMO) radio systems. Our experiments show that even with noisy velocity estimates and coarse map information, we achieve similar position accuracies

This paper investigates the asymptotic distribution of the K-fold cross validation error in an i.i.d. setting. As the number of observations n goes to infinity while keeping the number of folds K fixed, the K-fold cross validation error is √ n-consistent for the expected out-of-sample error and has an asymptotically normal distribution. A consistent estimate of the asymptotic variance is derived and used to construct asymptotically valid confidence intervals for the expected out-of-sample error. A hypothesis test is developed for comparing two estimators’ expected out-of-sample errors and a subsampling procedure is used to obtain critical values. Monte Carlo simulations demonstrate the asymptotic validity of our confidence intervals for the expected out-of-sample error and investigate the size and power properties of our test. In our empirical application, we use our estimator selection test to compare the out-of-sample predictive performance of OLS, Neural Networks, and Random Forests for predicting the sale price of a domain name in a GoDaddy expiry auction.

We study mean-field variational inference in a Bayesian linear model when the sample size n is comparable to the dimension p. In high dimensions, the common approach of minimizing a Kullback-Leibler divergence from the posterior distribution, or maximizing an evidence lower bound, may deviate from the true posterior mean and underestimate posterior uncertainty. We study instead minimization of the TAP free energy, showing in a high-dimensional asymptotic framework that it has a local minimizer which provides a consistent estimate of the posterior marginals and may be used for correctly calibrated posterior inference. Geometrically, we show that the landscape of the TAP free energy is strongly convex in an extensive neighborhood of this local minimizer, which under certain general conditions can be found by an Approximate Message Passing (AMP) algorithm. We then exhibit an efficient algorithm that linearly converges to the minimizer within this local neighborhood. In settings where it is conjectured that no efficient algorithm can find this local neighborhood, we prove analogous geometric properties for a local minimizer of the TAP free energy reachable by AMP, and show that posterior inference based on this minimizer remains correctly calibrated.

Variance in predictions across different trained models is a significant, under-explored source of error in fair binary classification. In practice, the variance on some data examples is so large that decisions can be effectively arbitrary. To investigate this problem, we take an experimental approach and make four overarching contributions: We: 1) Define a metric called self-consistency, derived from variance, which we use as a proxy for measuring and reducing arbitrariness; 2) Develop an ensembling algorithm that abstains from classification when a prediction would be arbitrary; 3) Conduct the largest to-date empirical study of the role of variance (vis-a-vis self-consistency and arbitrariness) in fair binary classification; and, 4) Release a toolkit that makes the US Home Mortgage Disclosure Act (HMDA) datasets easily usable for future research. Altogether, our experiments reveal shocking insights about the reliability of conclusions on benchmark datasets. Most fair binary classification benchmarks are close-to-fair when taking into account the amount of arbitrariness present in predictions -- before we even try to apply any fairness interventions. This finding calls into question the practical utility of common algorithmic fairness methods, and in turn suggests that we should reconsider how we choose to measure fairness in binary classification.

Despite the significant interest and progress in reinforcement learning (RL) problems with adversarial corruption, current works are either confined to the linear setting or lead to an undesired $\tilde{O}(\sqrt{T}\zeta)$ regret bound, where $T$ is the number of rounds and $\zeta$ is the total amount of corruption. In this paper, we consider the contextual bandit with general function approximation and propose a computationally efficient algorithm to achieve a regret of $\tilde{O}(\sqrt{T}+\zeta)$. The proposed algorithm relies on the recently developed uncertainty-weighted least-squares regression from linear contextual bandit and a new weighted estimator of uncertainty for the general function class. In contrast to the existing analysis that heavily relies on the linear structure, we develop a novel technique to control the sum of weighted uncertainty, thus establishing the final regret bounds. We then generalize our algorithm to the episodic MDP setting and first achieve an additive dependence on the corruption level $\zeta$ in the scenario of general function approximation. Notably, our algorithms achieve regret bounds either nearly match the performance lower bound or improve the existing methods for all the corruption levels and in both known and unknown $\zeta$ cases.

Multi-document summarization (MDS) is a difficult task in Natural Language Processing, aiming to summarize information from several documents. However, the source documents are often insufficient to obtain a qualitative summary. We propose a retriever-guided model combined with non-parametric memory for summary generation. This model retrieves relevant candidates from a database and then generates the summary considering the candidates with a copy mechanism and the source documents. The retriever is implemented with Approximate Nearest Neighbor Search (ANN) to search large databases. Our method is evaluated on the MultiXScience dataset which includes scientific articles. Finally, we discuss our results and possible directions for future work.

I spent most of the summer sifting through topics, including patents, blood diamonds and police brutality. None of them really stuck. However, on September 16, 2021 I sent Dr. White this email: " In a shocking turn of events, I have found another thing I would like to research. I would like to see if Twitter "coverage" of a publicly traded stock or related phrase ("google" and "search engine") can predict the daily returns of the stock, or changes in the highs/lows/volume of trades. The theory here being that investors' valuation of a stock may be reinforced or informed based on their perception of how others think about the companies (sort of like herd behavior) or their familiarity with the firm in general. If there is an effect, I would particularly like to examine whether this effect has gotten stronger during corona times, as many journalists are claiming that now that everyone is sitting at home with their commission-free trading apps like RobinHood, there are tons of amateur investors in the scene, who may be prone to "window shopping" for hot stocks that make the news.