Customer-obsessed science
Research areas
-
November 16, 202611 min readNew open-source tool turns existing test suites into sets of formal-verification tasks, which catch buggy solutions that tests alone would miss.
-
November 11, 20265 min read
-
-
-
Featured news
-
NeurIPS 2020 Workshop on Meta-learning2020Bayesian optimization (BO) is a popular method to optimize expensive blackbox functions. It efficiently tunes machine learning algorithms under the implicit assumption that hyperparameter evaluations cost approximately the same. In reality, the cost of evaluating different hyperparameters, be it in terms of time, dollars or energy, can span several orders of magnitude of difference. While a number of heuristics
-
NeurIPS 2020 Workshop on Offline Reinforcement Learning2020We study offline policy evaluation in a setting where the target policy can take actions that were not available when the data was logged. We analyze the bias of two popular regression-based estimators in this setting, and upper-bound their biases by a quantity we refer to as the reward regression risk. We show that the estimators can be asymptotically unbiased and uniformly convergent if the reward regression
-
NeurIPS 20202020We tackle the problem of predicting the number of optimization steps that a pretrained deep network needs to converge to a given value of the loss function. To do so, we leverage the fact that the training dynamics of a deep network during fine-tuning are well approximated by those of a linearized model. This allows us to approximate the training loss and accuracy at any point during training by solving
-
INLG 20202020Neural network based approaches to data-to-text natural language generation (NLG) have gained popularity in recent years, with the goal of generating a natural language prompt that accurately realizes an input meaning representation. To facilitate the training of neural network models, researchers created large datasets of paired utterances and their meaning representations. However, the creation of such
-
ICON 20202020Current voice assistants typically use the best hypothesis yielded by their Automatic Speech Recognition (ASR) module as input to their Natural Language Understanding (NLU) module, thereby losing helpful information that might be stored in lower-ranked ASR hypotheses. We explore the change in performance of NLU associated tasks when utilizing fivebest ASR hypotheses when compared to status quo for two language
Collaborations
View allWhether you're a faculty member or student, there are number of ways you can engage with Amazon.
View all