Publications

Multi-modality support has become an integral part of creating a seamless user experience with modern voice assistants with smart displays. Users refer to images, video thumbnails, or the accompanying text descriptions on the screen through voice communication with AI powered devices. This raises the need to either augment existing commercial voice only dialogue systems with state-of-the-art multimodal

Localizing defects in products is a critical component of industrial pipelines in manufacturing, retail, and many other industries to ensure consistent delivery of the highest quality products. Automated anomaly localization systems leveraging computer vision have the potential to replace laborious and subjective manual inspection of products. Recently, there have been tremendous efforts in the domain of

Self-supervised pretraining has advanced the capabilities of many computer vision tasks without requiring additional labels. One drawback is this technique requires extensive datasets and computational resources. This requirement of large datasets to pretrain with has often precluded the use of smaller, more niche datasets. Recently a method of pretraining has been developed that uses several stages of

Although black-box models can accurately predict outcomes such as weather patterns, they often lack transparency, making it challenging to extract meaningful insights (such as which atmospheric conditions signal future rainfall). Model explanations attempt to identify the essential features of a model, but these explanations can be inconsistent: two near-optimal models may admit vastly different explanations

User modeling is of great importance in personalization services. Many existing methods treat users as interaction sequences to capture users’ evolving interests. Another line of research models each user as a user graph in which the users’ interactions are modeled as nodes. Nodes (interactions) in user graphs are connected via edges that reflect certain relations such as item similarity. The graph-based

In this work, we investigate the possibility of using denoising diffusion models to learn priors for online decision making problems. Our special focus is on the meta-learning for bandit framework, with the goal of learning a strategy that performs well across bandit tasks of a same class. To this end, we train a diffusion model that learns the underlying task distribution and combine Thompson sampling

Transformer-based models demonstrate state of the art results on several natural language understanding tasks. However, their deployment comes at the cost of increased footprint and inference latency, limiting their adoption to real-time applications. Early exit strategies are designed to speed-up the inference by routing out a subset of samples at the earlier layers of the model. Exiting early causes losing

Quantum programs are written in high-level languages, whereas quantum hardware can only execute low-level native gates. To run programs on quantum systems, each highlevel instruction must be decomposed into native gates. This process is called gate nativization and is performed by the compiler. Recent quantum computers support a richer native gate set to reduce crosstalk by tackling frequency crowding and

Privacy-preserving federated learning (PPFL) is a paradigm of distributed privacy-preserving machine learning training in which a set of clients, each holding siloed training data, jointly compute a shared global model under the orchestration of an aggregation server. The system has the property that no party learns any information about any client’s training data, besides what could be inferred from the

Amazon and other e-commerce sites must employ mechanisms to protect their millions of customers from fraud, such as unauthorized use of credit cards. One such mechanism is order fraud evaluation, where systems evaluate orders for fraud risk, and either “pass” the order, or take an action to mitigate high risk. Order fraud evaluation systems typically use binary classification models that distinguish fraudulent

Evaluations in machine learning rarely use the latest metrics, datasets, or human evaluation in favor of remaining compatible with prior work. The compatibility, often facilitated through leaderboards, thus leads to outdated but standardized evaluation practices. We pose that the standardization is taking place in the wrong spot. Evaluation infrastructure should enable researchers to use the latest methods

In this paper, we tackle the problem of self supervised pre-training of deep neural networks for large scale tabular data in online advertising. Self supervised learning has recently been very effective for pre-training representations in domains such as vision, natural language processing, etc. But unlike these, designing self supervised learning tasks for tabular data is inherently challenging. Tabular

This paper quantifies the coverage area of Low-Power Wide-Area Networks (LPWAN) for Packet Success Rates (PSR) above 85%, where acceptable Quality of Service (QoS) can be achieved. The network consists of battery-operated end-nodes (ENs) and multiple stationary gateways (GWs). We consider asynchronous communication that uses ALOHA-based random channel access. Each transmission from the ENs can be received

Factual and logical errors made by Natural Language Generation (NLG) systems limit their applicability in many settings. We study this problem in a conversational search and recommendation setting, and observe that we can often make two simplifying assumptions in this domain: (i) there exists a body of structured knowledge we can use for verifying factuality of generated text; and (ii) the text to be factually

Machine learning models used for predictive modeling tasks spanning across personalization, recommender systems, ad response prediction, fraud detection etc. typically require a variety of tabular as well as sequential activity features about the user. For tasks like click-through or conversion (purchase) rate prediction where labeled data is available at scale, popular methods use deep sequence models