We introduce a Content-based Document Alignment approach (CDA), an efficient method to align multilingual web documents based on content in creating parallel training data for machine translation (MT) systems operating at the industrial level. CDA works in two steps: (i) projecting documents of a web domain to a shared multilingual space; then (ii) aligning them based on the similarity of their representations in such space. We leverage lexical translation models to build vector representations using TF-IDF. CDA achieves performance comparable with state-of-the-art systems in the WMT-16 Bilingual Document Alignment Shared Task benchmark while operating in multilingual space. Besides, we created two web-scale datasets to examine the robustness of CDA in an industrial setting involving up to 28 languages and millions of documents. The experiments show that CDA is robust, cost-effective, and is significantly superior in (i) processing large and noisy web data and (ii) scaling to new and low-resourced languages.

Implicit regularization in deep learning is perceived as a tendency of gradient-based optimization to fit training data with predictors of minimal "complexity." The fact that only some types of data give rise to generalization is understood to result from them being especially amenable to fitting with low complexity predictors. A major challenge towards formalizing this intuition is to define complexity measures that are quantitative yet capture the essence of data that admits generalization. With an eye towards this challenge, we analyze the implicit regularization in tensor factorization, equivalent to a certain non-linear neural network. We characterize the dynamics that gradient descent induces on the factorization, and establish a bias towards low tensor rank, in compliance with existing empirical evidence. Then, motivated by tensor rank capturing implicit regularization of a non-linear neural network, we empirically explore it as a measure of complexity, and find that it stays extremely low when fitting standard datasets. This leads us to believe that tensor rank may pave way to explaining both implicit regularization of neural networks, and the properties of real-world data translating it to generalization.

Generating functions, which are widely used in combinatorics and probability theory, encode function values into the coefficients of a polynomial. In this paper, we explore their use as a tractable probabilistic model, and propose probabilistic generating circuits (PGCs) for their efficient representation. PGCs strictly subsume many existing tractable probabilistic models, including determinantal point processes (DPPs), probabilistic circuits (PCs) such as sum-product networks, and tractable graphical models. We contend that PGCs are not just a theoretical framework that unifies vastly different existing models, but also show huge potential in modeling realistic data. We exhibit a simple class of PGCs that are not trivially subsumed by simple combinations of PCs and DPPs, and obtain competitive performance on a suite of density estimation benchmarks. We also highlight PGCs' connection to the theory of strongly Rayleigh distributions.

We propose a novel approach to interactive theorem-proving (ITP) using deep reinforcement learning. Unlike previous work, our framework is able to prove theorems both end-to-end and from scratch (i.e., without relying on example proofs from human experts). We formulate the process of ITP as a Markov decision process (MDP) in which each state represents a set of potential derivation paths. The agent learns to select promising derivations as well as appropriate tactics within each derivation using deep policy gradients. This structure allows us to introduce a novel backtracking mechanism which enables the agent to efficiently discard (predicted) dead-end derivations and restart the derivation from promising alternatives. Experimental results show that the framework provides comparable performance to that of the approaches that use human experts, and that it is also capable of proving theorems that it has never seen during training. We further elaborate the role of each component of the framework using ablation studies.

After a thankfully uneventful seven-month journey, NASA's Mars 2020 mission is set to safely reach the Red Planet and insert itself into orbit on Thursday ahead of deploying the Perseverance rover and Ingenuity helicopter prototype that it's been toting down to the planet's surface in search for evidence of ancient microbial life. However, this expedition has been in the works for far longer than Perseverance has been travelling through interplanetary space. First announced in 2012, the mission marks the culmination of nearly a decade's work by hundreds of machinists, designers, rocket scientists and engineers at NASA's Jet Propulsion Lab. But not just anyone can get hired there, working for the world's premiere spacecraft production facility and building equipment that will grace the surfaces of neighboring planets. For Mohamed Abid, a Deputy Chief Mechanical Engineer on the Mars 2020 mission, the path to working at the JPL began in Tunisia, where he grew up.

There has been an increasing demand for demographic modelling and forecasting over the last few decades, driven by many developed countries are now suffering a rapid decline in mortality and fertility, leading to a significant increase in expenditures on health services for an ageing population and a shortage of future labour. A better understanding of the mortality and fertility patterns and trends is always of importance for all stakeholders in a society as the mortality forecasts, for example, play a vital role for the insurance and pensions industries in pricing their insurance products. The fertility predictions are also of great interest to the government and education sectors in planing children's welfare and educational services. Unlike the biological and the medical methods, statisticians have developed very different and purely mathematical methods to model the demographic patterns and trends which are well-documented by Preston et al. (2000). The history of demographic modelling with the mathematical approaches can be traced back to some deterministic models proposed in the midnineteenth century, see, for example, Gompertz (1825) and Makeham (1860). The deterministic models are, however, restricted with few fixed factors and have no stochastic process considered owing to the lack of computing capability in that early period.

It has been empirically observed that, in deep neural networks, the solutions found by stochastic gradient descent from different random initializations can be often connected by a path with low loss. Recent works have shed light on this intriguing phenomenon by assuming either the over-parameterization of the network or the dropout stability of the solutions. In this paper, we reconcile these two views and present a novel condition for ensuring the connectivity of two arbitrary points in parameter space. This condition is provably milder than dropout stability, and it provides a connection between the problem of finding low-loss paths and the memorization capacity of neural nets. This last point brings about a trade-off between the quality of features at each layer and the over-parameterization of the network. As an extreme example of this trade-off, we show that (i) if subsets of features at each layer are linearly separable, then almost no over-parameterization is needed, and (ii) under generic assumptions on the features at each layer, it suffices that the last two hidden layers have $\Omega(\sqrt{N})$ neurons, $N$ being the number of samples. Finally, we provide experimental evidence demonstrating that the presented condition is satisfied in practical settings even when dropout stability does not hold.

We consider learning to optimize a classification metric defined by a black-box function of the confusion matrix. Such black-box learning settings are ubiquitous, for example, when the learner only has query access to the metric of interest, or in noisy-label and domain adaptation applications where the learner must evaluate the metric via performance evaluation using a small validation sample. Our approach is to adaptively learn example weights on the training dataset such that the resulting weighted objective best approximates the metric on the validation sample. We show how to model and estimate the example weights and use them to iteratively post-shift a pre-trained class probability estimator to construct a classifier. We also analyze the resulting procedure's statistical properties. Experiments on various label noise, domain shift, and fair classification setups confirm that our proposal is better than the individual state-of-the-art baselines for each application.

Large amounts of threat intelligence information about mal-ware attacks are available in disparate, typically unstructured, formats. Knowledge graphs can capture this information and its context using RDF triples represented by entities and relations. Sparse or inaccurate threat information, however, leads to challenges such as incomplete or erroneous triples. Named entity recognition (NER) and relation extraction (RE) models used to populate the knowledge graph cannot fully guaran-tee accurate information retrieval, further exacerbating this problem. This paper proposes an end-to-end approach to generate a Malware Knowledge Graph called MalKG, the first open-source automated knowledge graph for malware threat intelligence. MalKG dataset called MT40K1 contains approximately 40,000 triples generated from 27,354 unique entities and 34 relations. We demonstrate the application of MalKGin predicting missing malware threat intelligence information in the knowledge graph. For ground truth, we manually curate a knowledge graph called MT3K, with 3,027 triples generated from 5,741 unique entities and 22 relations. For entity prediction via a state-of-the-art entity prediction model(TuckER), our approach achieves 80.4 for the hits@10 metric (predicts the top 10 options for missing entities in the knowledge graph), and 0.75 for the MRR (mean reciprocal rank). We also propose a framework to automate the extraction of thousands of entities and relations into RDF triples, both manually and automatically, at the sentence level from1,100 malware threat intelligence reports and from the com-mon vulnerabilities and exposures (CVE) database.

High-resolution mapping of cells and tissue structures provides a foundation for developing interpretable machine-learning models for computational pathology. Deep learning algorithms can provide accurate mappings given large numbers of labeled instances for training and validation. Generating adequate volume of quality labels has emerged as a critical barrier in computational pathology given the time and effort required from pathologists. In this paper we describe an approach for engaging crowds of medical students and pathologists that was used to produce a dataset of over 220,000 annotations of cell nuclei in breast cancers. We show how suggested annotations generated by a weak algorithm can improve the accuracy of annotations generated by non-experts and can yield useful data for training segmentation algorithms without laborious manual tracing. We systematically examine interrater agreement and describe modifications to the MaskRCNN model to improve cell mapping. We also describe a technique we call Decision Tree Approximation of Learned Embeddings (DTALE) that leverages nucleus segmentations and morphologic features to improve the transparency of nucleus classification models. The annotation data produced in this study are freely available for algorithm development and benchmarking at: https://sites.google.com/view/nucls .