3 citations · 6 across the 9 of their papers we have counts for
9 papers
STARIXNet: Multivariate and Multi-attribute Deep Learning Approach to Real-Time Resource Allocation in Cloud Platforms
Ahmed Abdulaal, Maruf Aytekin, Thilaga kumaran Srinivasan +1
Intelligent scaling of microservices in cloud platforms is crucial for mitigating escalating compute costs while avoiding service disruptions. Current solutions are limited to the…
ITEm: Unsupervised Image-Text Embedding Learning for eCommerce
Baohao Liao, Michael Kozielski, Sanjika Hewavitharana +3
Product embedding serves as a cornerstone for a wide range of applications in eCommerce. The product embedding learned from multiple modalities shows significant improvement over t…
Multi-armed bandits for resource efficient, online optimization of language model pre-training: the use case of dynamic masking
Iñigo Urteaga, Moulay-Zaïdane Draïdia, Tomer Lancewicki +1
We design and evaluate a Bayesian optimization framework for resource efficient pre-training of Transformer-based language models (TLMs). TLM pre-training requires high computation…
Towards Reinforcement Learning for Pivot-based Neural Machine Translation with Non-autoregressive Transformer
Evgeniia Tokarchuk, Jan Rosendahl, Weiyue Wang +4
Pivot-based neural machine translation (NMT) is commonly used in low-resource setups, especially for translation between non-English language pairs. It benefits from using high res…
Integrated Training for Sequence-to-Sequence Models Using Non-Autoregressive Transformer
Evgeniia Tokarchuk, Jan Rosendahl, Weiyue Wang +4
Complex natural language applications such as speech translation or pivot translation traditionally rely on cascaded models. However, cascaded models are known to be prone to error…
Deploying a BERT-based Query-Title Relevance Classifier in a Production System: a View from the Trenches
Leonard Dahlmann, Tomer Lancewicki
The Bidirectional Encoder Representations from Transformers (BERT) model has been radically improving the performance of many Natural Language Processing (NLP) tasks such as Text C…
Automatic and Simultaneous Adjustment of Learning Rate and Momentum for Stochastic Gradient Descent
Tomer Lancewicki, Selcuk Kopru
Stochastic Gradient Descent (SGD) methods are prominent for training machine learning and deep learning models. The performance of these techniques depends on their hyperparameter…
Sequential Inverse Approximation of a Regularized Sample Covariance Matrix
Tomer Lancewicki
One of the goals in scaling sequential machine learning methods pertains to dealing with high-dimensional data spaces. A key related challenge is that many methods heavily depend o…
Regularization of the Kernel Matrix via Covariance Matrix Shrinkage Estimation
Tomer Lancewicki
The kernel trick concept, formulated as an inner product in a feature space, facilitates powerful extensions to many well-known algorithms. While the kernel matrix involves inner p…