T
Timothy Nguyen
Researcher at Google
Publications - 26
Citations - 379
Timothy Nguyen is an academic researcher from Google. The author has contributed to research in topics: Boundary value problem & Boundary (topology). The author has an hindex of 8, co-authored 24 publications receiving 145 citations. Previous affiliations of Timothy Nguyen include California Institute of Technology & State University of New York System.
Papers
More filters
Posted Content
Measuring Calibration in Deep Learning
Jeremy Nixon,Michael W. Dusenberry,Ghassen Jerfel,Timothy Nguyen,Jeremiah Liu,Linchuan Zhang,Dustin Tran +6 more
TL;DR: A comprehensive empirical study of choices in calibration measures including measuring all probabilities rather than just the maximum prediction, thresholding probability values, class conditionality, number of bins, bins that are adaptive to the datapoint density, and the norm used to compare accuracies to confidences.
Posted Content
Dataset Meta-Learning from Kernel Ridge-Regression
TL;DR: This work introduces the novel concept of $\epsilon$-approximation of datasets, obtaining datasets which are much smaller than or are significant corruptions of the original training data while maintaining similar model performance.
Journal Article
Architecture Matters in Continual Learning
Seyed Iman Mirzadeh,Arslan Chaudhry,Dong Yin,Timothy Nguyen,R.P. Pascanu,Dilan Gorur,Mehrdad Farajtabar +6 more
TL;DR: It is shown that the choice of architecture can significantly impact the continual learning performance, and different architectures lead to different trade-offs between the ability to remember previous tasks and learning new ones.
Posted Content
Quantum Yang-Mills Theory in Two Dimensions: Exact versus Perturbative
TL;DR: In this paper, a mathematically rigorous formulation of the perturbative quantization of 2D Yang-Mills was provided, and the asymptotics of exact lattice Wilson loop expectations on $S^2$ were compared with perturbatively computed expectations in holomorphic gauge for simple closed curves to all orders.
Journal ArticleDOI
Quantization of the nonlinear sigma model revisited
TL;DR: In this article, the authors revisit the subject of perturbatively quantizing the nonlinear sigma model in two dimensions from a rigorous, mathematical point of view, and make precise the cohomological problem of eliminating potential anomalies that may arise when trying to preserve symmetries under quantization.