arXiv subjects

Yixin Wang

Publications and source records attributed to Yixin Wang.

At least 145 records · Page 8Linked to original sources

arXiv2020

Variational Bayes under Model Misspecification

Variational Bayes (VB) is a scalable alternative to Markov chain Monte Carlo (MCMC) for Bayesian posterior inference. Though popular, VB comes with few theoretical guarantees, most of which focus on well-specified models. However, models are rarely well-specified in practice. In this work, we study VB under model misspecification. We prove the VB posterior is asymptotically normal and centers at the value that minimizes the Kullback-Leibler (KL) divergence to the true data-generating distribution. Moreover, the VB posterior mean centers at the same value and is also asymptotically normal. These results generalize the variational Bernstein--von Mises theorem [29] to misspecified models. As a consequence of these results, we find that the model misspecification error dominates the variational approximation error in VB posterior predictive distributions. It explains the widely observed phenomenon that VB achieves comparable predictive accuracy with MCMC even though VB uses an approximating family. As illustrations, we study VB under three forms of model misspecification, ranging from model over-/under-dispersion to latent dimensionality misspecification. We conduct two simulation studies that demonstrate the theoretical results.

stat.ML↗

arXiv2020

The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 Challenge

There is a large body of literature linking anatomic and geometric characteristics of kidney tumors to perioperative and oncologic outcomes. Semantic segmentation of these tumors and their host kidneys is a promising tool for quantitatively characterizing these lesions, but its adoption is limited due to the manual effort required to produce high-quality 3D segmentations of these structures. Recently, methods based on deep learning have shown excellent results in automatic 3D segmentation, but they require large datasets for training, and there remains little consensus on which methods perform best. The 2019 Kidney and Kidney Tumor Segmentation challenge (KiTS19) was a competition held in conjunction with the 2019 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) which sought to address these issues and stimulate progress on this automatic segmentation problem. A training set of 210 cross sectional CT images with kidney tumors was publicly released with corresponding semantic segmentation masks. 106 teams from five continents used this data to develop automated systems to predict the true segmentation masks on a test set of 90 CT images for which the corresponding ground truth segmentations were kept private. These predictions were scored and ranked according to their average So rensen-Dice coefficient between the kidney and tumor across all 90 cases. The winning team achieved a Dice of 0.974 for kidney and 0.851 for tumor, approaching the inter-annotator performance on kidney (0.983) but falling short on tumor (0.923). This challenge has now entered an "open leaderboard" phase where it serves as a challenging benchmark in 3D semantic segmentation.

eess.IV↗

arXiv2020

The 2020 release of the ExoMol database: molecular line lists for exoplanet and other hot atmospheres

The ExoMol database (www.exomol.com) provides molecular data for spectroscopic studies of hot atmospheres. While the data is intended for studies of exoplanets and other astronomical bodies, the dataset is widely applicable. The basic form of the database is extensive line lists; these are supplemented with partition functions, state lifetimes, cooling functions, Landé g-factors, temperature-dependent cross sections, opacities, pressure broadening parameters, $k$-coefficients and dipoles. This paper presents the latest release of the database which has been expanded to consider 80 molecules and 190 isotopologues totaling over 700 billion transitions. While the spectroscopic data is concentrated at infrared and visible wavelengths, ultraviolet transitions are being increasingly considered in response to requests from observers. The core of the database comes from the ExoMol project which primarily uses theoretical methods, albeit usually fine-tuned to reproduce laboratory spectra, to generate very extensive line lists for studies of hot bodies. The data has recently been supplemented by line lists deriving from direct laboratory observations, albeit usually with the use of ab initio transition intensities. A major push in the new release is towards accurate characterisation of transition frequencies for use in high resolution studies of exoplanets and other bodies.

astro-ph.SR↗

arXiv2020

Thermodynamically Stable DNA Code Design using a Similarity Significance Model

DNA code design aims to generate a set of DNA sequences (codewords) with minimum likelihood of undesired hybridizations among sequences and their reverse-complement (RC) pairs (cross-hybridization). Inspired by the distinct hybridization affinities (or stabilities) of perfect double helix constructed by individual single-stranded DNA (ssDNA) and its RC pair, we propose a novel similarity significance (SS) model to measure the similarity between DNA sequences. Particularly, instead of directly measuring the similarity of two sequences by any metric/approach, the proposed SS works in a way to evaluate how more likely will the undesirable hybridizations occur over the desirable hybridizations in the presence of the two measured sequences and their RC pairs. With this SS model, we construct thermodynamically stable DNA codes subject to several combinatorial constraints using a sorting-based algorithm. The proposed scheme results in DNA codes with larger code sizes and wider free energy gaps (hence better cross-hybridization performance) compared to the existing methods.

cs.IT↗

arXiv2020

Cascaded Volumetric Convolutional Network for Kidney Tumor Segmentation from CT volumes

Automated segmentation of kidney and tumor from 3D CT scans is necessary for the diagnosis, monitoring, and treatment planning of the disease. In this paper, we describe a two-stage framework for kidney and tumor segmentation based on 3D fully convolutional network (FCN). The first stage preliminarily locate the kidney and cut off the irrelevant background to reduce class imbalance and computation cost. Then the second stage precisely segment the kidney and tumor on the cropped patch. The proposed method ranks the 4th place out of 105 competitive teams in MICCAI 2019 KiTS Challenge with a Composite Dice of 90.24%.

eess.IV↗

arXiv2020

Towards Clarifying the Theory of the Deconfounder

Wang and Blei (2019) studies multiple causal inference and proposes the deconfounder algorithm. The paper discusses theoretical requirements and presents empirical studies. Several refinements have been suggested around the theory of the deconfounder. Among these, Imai and Jiang clarified the assumption of "no unobserved single-cause confounders." Using their assumption, this paper clarifies the theory. Furthermore, Ogburn et al. (2020) proposes counterexamples to the theory. But the proposed counterexamples do not satisfy the required assumptions.

stat.ML↗

arXiv2020

Harmonics Based Representation in Clarinet Tone Quality Evaluation

Music tone quality evaluation is generally performed by experts. It could be subjective and short of consistency and fairness as well as time-consuming. In this paper we present a new method for identifying the clarinet reed quality by evaluating tone quality based on the harmonic structure and energy distribution. We first decouple the quality of reed and clarinet pipe based on the acoustic harmonics, and discover that the reed quality is strongly relevant to the even parts of the harmonics. Then we construct a features set consisting of the even harmonic envelope and the energy distribution of harmonics in spectrum. The annotated clarinet audio data are recorded from 3 levels of performers and the tone quality is classified by machine learning. The results show that our new method for identifying low and medium high tones significantly outperforms previous methods.

cs.SD↗

arXiv2020

Empirical Line Lists in the ExoMol Database

The ExoMol database aims to provide comprehensive molecular line lists for exoplanetary and other hot atmospheres. The data are expanded by inclusion of empirically derived line lists taken from the literature for a series of diatomic molecules, namely CH, NH, OH, AlCl, AlF, OH$^+$, CaF, MgF, KF, NaF, LiCl, LiF, MgH, TiH, CrH, FeH, C$_2$, CP, CN, CaH, and triplet N$_2$. Generally, these line lists are constructed from measured spectra using a combination of effective rotational Hamiltonian models for the line positions and ab initio (transition) dipole moments to provide intensities. This work results in the inclusion of 22 new molecules (36 new isotopologues) in the ExoMol database.

astro-ph.SR↗

arXiv2019

The Blessings of Multiple Causes: A Reply to Ogburn et al. (2019)

Ogburn et al. (2019, arXiv:1910.05438) discuss "The Blessings of Multiple Causes" (Wang and Blei, 2018, arXiv:1805.06826). Many of their remarks are interesting. But they also claim that the paper has "foundational errors" and that its "premise is...incorrect." These claims are not substantiated. There are no foundational errors; the premise is correct.

stat.ML↗

arXiv2019

Augmented Unlocking Techniques for Smartphones Using Pre-Touch Information

Smartphones store a significant amount of personal and private information, and are playing an increasingly important role in people's lives. It is important for authentication techniques to be more resistant against two known attacks called shoulder surfing and smudge attacks. In this work, we propose a new technique called 3D Pattern. Our 3D Pattern technique takes advantage of a new input paradigm called pre-touch, which could soon allow smartphones to sense a user's finger position at some distance from the screen. We implement the technique and evaluate it in a pilot study (n=6) by comparing it to PIN and pattern locks. Our results show that although our prototype takes about 8 seconds to authenticate, it is immune to smudge attacks and promises to be more resistant to shoulder surfing.

cs.CR↗

arXiv2019

The Medical Deconfounder: Assessing Treatment Effects with Electronic Health Records

The treatment effects of medications play a key role in guiding medical prescriptions. They are usually assessed with randomized controlled trials (RCTs), which are expensive. Recently, large-scale electronic health records (EHRs) have become available, opening up new opportunities for more cost-effective assessments. However, assessing a treatment effect from EHRs is challenging: it is biased by unobserved confounders, unmeasured variables that affect both patients' medical prescription and their outcome, e.g. the patients' social economic status. To adjust for unobserved confounders, we develop the medical deconfounder, a machine learning algorithm that unbiasedly estimates treatment effects from EHRs. The medical deconfounder first constructs a substitute confounder by modeling which medications were prescribed to each patient; this substitute confounder is guaranteed to capture all multi-medication confounders, observed or unobserved (arXiv:1805.06826). It then uses this substitute confounder to adjust for the confounding bias in the analysis. We validate the medical deconfounder on two simulated and two real medical data sets. Compared to classical approaches, the medical deconfounder produces closer-to-truth treatment effect estimates; it also identifies effective medications that are more consistent with the findings in the medical literature.

stat.ML↗

arXiv2019

Multimodal Data Fusion of Non-Gaussian Spatial Fields in Sensor Networks

We develop a robust data fusion algorithm for field reconstruction of multiple physical phenomena. The contribution of this paper is twofold: First, we demonstrate how multi-spatial fields which can have any marginal distributions and exhibit complex dependence structures can be constructed. To this end we develop a model where a latent process of these physical phenomena is modelled as Multiple Gaussian Process (MGP), and the dependence structure between these phenomena is captured through a Copula process. This model has the advantage of allowing one to choose any marginal distributions for the physical phenomenon. Second, we develop an efficient and robust linear estimation algorithm to predict the mean behaviour of the physical phenomena using rank correlation instead of the conventional linear Pearson correlation. Our approach has the advantage of avoiding the need to derive intractable predictive posterior distribution and also has a tractable solution for the rank correlation values. We show that our model outperforms the model which uses the conventional linear Pearson correlation metric in terms of the prediction mean-squared-errors (MSE). This provides the motivation for using our models for multimodal data fusion.

stat.ME↗

arXiv2019

Using Embeddings to Correct for Unobserved Confounding in Networks

We consider causal inference in the presence of unobserved confounding. We study the case where a proxy is available for the unobserved confounding in the form of a network connecting the units. For example, the link structure of a social network carries information about its members. We show how to effectively use the proxy to do causal inference. The main idea is to reduce the causal estimation problem to a semi-supervised prediction of both the treatments and outcomes. Networks admit high-quality embedding models that can be used for this semi-supervised prediction. We show that the method yields valid inferences under suitable (weak) conditions on the quality of the predictive model. We validate the method with experiments on a semi-synthetic social network dataset. Code is available at github.com/vveitch/causal-network-embeddings.

stat.ML↗

arXiv2019

Multiple Causes: A Causal Graphical View

Unobserved confounding is a major hurdle for causal inference from observational data. Confounders---the variables that affect both the causes and the outcome---induce spurious non-causal correlations between the two. Wang & Blei (2018) lower this hurdle with "the blessings of multiple causes," where the correlation structure of multiple causes provides indirect evidence for unobserved confounding. They leverage these blessings with an algorithm, called the deconfounder, that uses probabilistic factor models to correct for the confounders. In this paper, we take a causal graphical view of the deconfounder. In a graph that encodes shared confounding, we show how the multiplicity of causes can help identify intervention distributions. We then justify the deconfounder, showing that it makes valid inferences of the intervention. Finally, we expand the class of graphs, and its theory, to those that include other confounders and selection variables. Our results expand the theory in Wang & Blei (2018), justify the deconfounder for causal graphs, and extend the settings where it can be used.

stat.ML↗

arXiv2019

Equal Opportunity and Affirmative Action via Counterfactual Predictions

Machine learning (ML) can automate decision-making by learning to predict decisions from historical data. However, these predictors may inherit discriminatory policies from past decisions and reproduce unfair decisions. In this paper, we propose two algorithms that adjust fitted ML predictors to make them fair. We focus on two legal notions of fairness: (a) providing equal opportunity (EO) to individuals regardless of sensitive attributes and (b) repairing historical disadvantages through affirmative action (AA). More technically, we produce fair EO and AA predictors by positing a causal model and considering counterfactual decisions. We prove that the resulting predictors are theoretically optimal in predictive performance while satisfying fairness. We evaluate the algorithms, and the trade-offs between accuracy and fairness, on datasets about admissions, income, credit and recidivism.

stat.ML↗

arXiv2019

The Deconfounded Recommender: A Causal Inference Approach to Recommendation

The goal of recommendation is to show users items that they will like. Though usually framed as a prediction, the spirit of recommendation is to answer an interventional question---for each user and movie, what would the rating be if we "forced" the user to watch the movie? To this end, we develop a causal approach to recommendation, one where watching a movie is a "treatment" and a user's rating is an "outcome." The problem is there may be unobserved confounders, variables that affect both which movies the users watch and how they rate them; unobserved confounders impede causal predictions with observational data. To solve this problem, we develop the deconfounded recommender, a way to use classical recommendation models for causal recommendation. Following Wang & Blei [23], the deconfounded recommender involves two probabilistic models. The first models which movies the users watch; it provides a substitute for the unobserved confounders. The second one models how each user rates each movie; it employs the substitute to help account for confounders. This two-stage approach removes bias due to confounding. It improves recommendation and enjoys stable performance against interventions on test sets.

cs.IR↗

arXiv2019

Minimal Dispersion Approximately Balancing Weights: Asymptotic Properties and Practical Considerations

Weighting methods are widely used to adjust for covariates in observational studies, sample surveys, and regression settings. In this paper, we study a class of recently proposed weighting methods which find the weights of minimum dispersion that approximately balance the covariates. We call these weights "minimal weights" and study them under a common optimization framework. The key observation is the connection between approximate covariate balance and shrinkage estimation of the propensity score. This connection leads to both theoretical and practical developments. From a theoretical standpoint, we characterize the asymptotic properties of minimal weights and show that, under standard smoothness conditions on the propensity score function, minimal weights are consistent estimates of the true inverse probability weights. Also, we show that the resulting weighting estimator is consistent, asymptotically normal, and semiparametrically efficient. From a practical standpoint, we present a finite sample oracle inequality that bounds the loss incurred by balancing more functions of the covariates than strictly needed. This inequality shows that minimal weights implicitly bound the number of active covariate balance constraints. We finally provide a tuning algorithm for choosing the degree of approximate balance in minimal weights. We conclude the paper with four empirical studies that suggest approximate balance is preferable to exact balance, especially when there is limited overlap in covariate distributions. In these studies, we show that the root mean squared error of the weighting estimator can be reduced by as much as a half with approximate balance.

stat.ME↗

arXiv2019

The Blessings of Multiple Causes

Causal inference from observational data often assumes "ignorability," that all confounders are observed. This assumption is standard yet untestable. However, many scientific studies involve multiple causes, different variables whose effects are simultaneously of interest. We propose the deconfounder, an algorithm that combines unsupervised machine learning and predictive model checking to perform causal inference in multiple-cause settings. The deconfounder infers a latent variable as a substitute for unobserved confounders and then uses that substitute to perform causal inference. We develop theory for the deconfounder, and show that it requires weaker assumptions than classical causal inference. We analyze its performance in three types of studies: semi-simulated data around smoking and lung cancer, semi-simulated data around genome-wide association studies, and a real dataset about actors and movie revenue. The deconfounder provides a checkable approach to estimating closer-to-truth causal effects.

stat.ML↗