Zobrazeno 1 - 10
of 77
pro vyhledávání: '"Ke, Alexander"'
Autor:
Wang, Ke Alexander, Fox, Emily B.
Diabetes encompasses a complex landscape of glycemic control that varies widely among individuals. However, current methods do not faithfully capture this variability at the meal level. On the one hand, expert-crafted features lack the flexibility of
Externí odkaz:
http://arxiv.org/abs/2312.03344
Efficiently capturing the long-range patterns in sequential data sources salient to a given task -- such as classification and generative modeling -- poses a fundamental challenge. Popular approaches in the space tradeoff between the memory burden of
Externí odkaz:
http://arxiv.org/abs/2305.01638
Traditional models of glucose-insulin dynamics rely on heuristic parameterizations chosen to fit observations within a laboratory setting. However, these models cannot describe glucose dynamics in daily life. One source of failure is in their descrip
Externí odkaz:
http://arxiv.org/abs/2304.14300
Autor:
Ke, Alexander, Huang, Shih-Cheng, O'Connell, Chloe P, Klimont, Michal, Yeung, Serena, Rajpurkar, Pranav
Pretraining on large natural image classification datasets such as ImageNet has aided model development on data-scarce 2D medical tasks. 3D medical tasks often have much less data than 2D medical tasks, prompting practitioners to rely on pretrained 2
Externí odkaz:
http://arxiv.org/abs/2304.00546
Importance weighting is a classic technique to handle distribution shifts. However, prior work has presented strong empirical and theoretical evidence demonstrating that importance weights can have little to no effect on overparameterized neural netw
Externí odkaz:
http://arxiv.org/abs/2112.12986
We consider the problem of probabilistic forecasting over categories with graph structure, where the dynamics at a vertex depends on its local connectivity structure. We present GOPHER, a method that combines the inductive bias of graph neural networ
Externí odkaz:
http://arxiv.org/abs/2112.09964
State-of-the-art methods for scalable Gaussian processes use iterative algorithms, requiring fast matrix vector multiplies (MVMs) with the covariance kernel. The Structured Kernel Interpolation (SKI) framework accelerates these MVMs by performing eff
Externí odkaz:
http://arxiv.org/abs/2106.06695
In many real-world problems, we want to infer some property of an expensive black-box function $f$, given a budget of $T$ function evaluations. One example is budget constrained global optimization of $f$, for which Bayesian optimization is a popular
Externí odkaz:
http://arxiv.org/abs/2104.09460
CheXtransfer: Performance and Parameter Efficiency of ImageNet Models for Chest X-Ray Interpretation
Deep learning methods for chest X-ray interpretation typically rely on pretrained models developed for ImageNet. This paradigm assumes that better ImageNet architectures perform better on chest X-ray tasks and that ImageNet-pretrained weights provide
Externí odkaz:
http://arxiv.org/abs/2101.06871
Reasoning about the physical world requires models that are endowed with the right inductive biases to learn the underlying dynamics. Recent works improve generalization for predicting trajectories by learning the Hamiltonian or Lagrangian of a syste
Externí odkaz:
http://arxiv.org/abs/2010.13581