Publications

Deep learning based forecasting methods have become the methods of choice in many applications of time series prediction or forecasting often outperforming other approaches. Consequently, over the last years, these methods are now ubiquitous in large-scale industrial forecasting applications and have consistently ranked among the best entries in forecasting competitions(e.g.,M4andM5). This practical success

Probabilistic inference of Neural Network parameters is challenging due to the highly multi-modal likelihood functions. Most importantly, the permutation invariance of the neurons of the hidden layers renders the likelihood function unidentifiable with a factorial number of equivalent (symmetric) modes, independent of the data. We show that variational Bayesian methods that approximate the (multi-modal)

The rise of programmable quantum devices has motivated the exploration of circuit models which could realize novel physics. A promising candidate is a class of hybrid circuits, where entangling unitary dynamics compete with disentangling measurements. Novel phase transitions between different entanglement regimes have been identified in their dynamical states, with universal properties hinting at unexplored

The Principle of Insufficient Reason (PIR) assigns equal probabilities to each alternative of a random experiment whenever there is no reason to prefer one over the other. The Maximum Entropy Principle (MaxEnt) generalizes PIR to the case where statistical information like expectations are given. It is known that both principles result in paradoxical probability updates for joint distributions of cause

In this article, we explain why an interventional view of recommendation provides a rigorous framework for thinking about recommender systems—enabling new insights both at a technical level for evaluation and learning, as well as at a conceptual level when we reason about the future of recommender systems. In some respects, the view of recommender systems as autonomous systems that act through their recommendations

The authors enhance pretrained language models with Securities and Exchange Commission filings data to create better language representations for features used in a predictive model. Specifically, they train RoBERTa class models with additional financial regulatory text, which they denote as a class of RoBERTa-Fin models. Using different datasets, the authors assess whether there is material improvement

The prevalence of approaches based on gradient boosted trees among the top contestants in the M5 competition is potentially the most eye-catching result. Tree-based methods out-shone other solutions, in particular deep learning-based solutions. The winners in both tracks of the M5 competition heavily relied on them. This prevalence is even more remarkable given the dominance of other methods in the literature

Automatically detecting anomalies in event data can provide substantial value in domains such as healthcare, DevOps, and information security. In this paper, we frame the problem of detecting anomalous continuous-time event sequences as out-of-distribution (OoD) detection for temporal point processes (TPPs). We show how this problem can be approached using tools from the goodness-of-fit (GoF) testing literature

Time series data are often corrupted by outliers or other kinds of anomalies. Identifying the anomalous points can be a goal on its own (anomaly detection), or a means to improving performance of other time series tasks (e.g. forecasting). Recent deep-learning-based approaches to anomaly detection and forecasting commonly assume that the proportion of anomalies in the training data is small enough to ignore

As cloud computing resources become more adopted, the infrastructures in which they are used naturally grow in the amount of resources and overall complexity, becoming harder to manage. Infrastructure-as-Code (IaC) is presented as a solution to this problem, allowing developers to manage and provision these cloud resources programmatically. The infrastructure is then maintained through a code base, allowing

Open-book question answering is a subset of question answering (QA) tasks where the system aims to find answers in a given set of documents (open-book) and common knowledge about a topic. This article proposes a solution for answering natural language questions from a corpus of Amazon Web Services (AWS) technical documents with no domain-specific labeled data (zero-shot). These questions have a yes–no–none

As quantum computers approach the fault tolerance threshold, diagnosing and characterizing the noise on large scale quantum devices is increasingly important. One of the most important classes of noise channels is the class of Pauli channels, for reasons of both theoretical tractability and experimental relevance. Here we present a practical algorithm for estimating the s nonzero Pauli error rates in an

Recommending sets of items that include both personalized and compatible items is crucial to personalized styling programs such as Amazon’s Personal Shopper. There is both an extensive literature on learning generic fashion compatibility and also on personalization in fashion. However, recommending pairs of items that the customer would like to wear together is still less studied as it involves learning

Training neural machine translation (NMT) models in federated learning (FL) settings could be inefficient both computationally and communication-wise, due to the large size of translation engines as well as the multiple rounds of updates required to train clients and a central server. In this paper, we explore how to efficiently build NMT models in an FL setup by proposing a novel solution. In order to

Adversarial attack on question answering systems over tabular data (TableQA) can help evaluate to what extent TableQA systems can understand natural language questions and reason with tables. However, generating natural language adversarial questions is difficult, because even a single character swap could lead to huge semantic difference in human perception. In this paper, we propose SAGE (Semantically