Search Results for author:
Found 9 papers, 2 papers with code
Unsupervised Adaptation of Question Answering Systems via Generative Self-training
Nevertheless, additional pre-training closer to the end-task, such as training on synthetic QA pairs, has been shown to improve performance.
Minimum-Norm Interpolation Under Covariate Shift
We follow our analysis with empirical studies that show these beneficial and malignant covariate shifts for linear interpolators on real image data, and for fully-connected neural networks in settings where the input data dimension is larger than the training sample size.
The Calibration Generalization Gap
We propose a systematic way to study the calibration error: by decomposing it into (1) calibration error on the train set, and (2) the calibration generalization gap.
Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting
In this work we argue that while benign overfitting has been instructive and fruitful to study, many real interpolating methods like neural networks do not fit benignly: modest noise in the training set causes nonzero (but non-infinite) excess risk at test time, implying these models are neither benign nor catastrophic but rather fall in an intermediate regime.
Iterative Data Programming for Expanding Text Classification Corpora
Real-world text classification tasks often require many labeled training examples that are expensive to obtain.
Multi-Frame Cross-Entropy Training for Convolutional Neural Networks in Speech Recognition
We introduce Multi-Frame Cross-Entropy training (MFCE) for convolutional neural network acoustic models.
Bootstrapping Conversational Agents With Weak Supervision
We report on a user study that shows positive user feedback for this new approach to build conversational agents, and demonstrates the effectiveness of using data programming for auto-labeling.
Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech Recognition
The proposed approach demonstrates improvement of model efficiency and performance on both object recognition and speech recognition tasks, using popular architectures including ResNet and ResNeXt.
Deep Canonically Correlated LSTMs
We examine Deep Canonically Correlated LSTMs as a way to learn nonlinear transformations of variable length sequences and embed them into a correlated, fixed dimensional space.
