Search Results for author: Ke Alexander Wang

Found 8 papers, 5 papers with code

Is Importance Weighting Incompatible with Interpolating Classifiers?

1 code implementation ICLR 2022 Ke Alexander Wang, Niladri S. Chatterji, Saminul Haque, Tatsunori Hashimoto

As a remedy, we show that polynomially-tailed losses restore the effects of importance reweighting in correcting distribution shift in overparameterized models.

GOPHER: Categorical probabilistic forecasting with graph structure via local continuous-time dynamics

no code implementations18 Dec 2021 Ke Alexander Wang, Danielle Maddix, Yuyang Wang

We consider the problem of probabilistic forecasting over categories with graph structure, where the dynamics at a vertex depends on its local connectivity structure.

GOPHER: Categorical probabilistic forecasting withgraph structure via local continuous-time dynamics

no code implementations NeurIPS Workshop ICBINB 2021 Ke Alexander Wang, Danielle C. Maddix, Bernie Wang

We consider the problem of probabilistic forecasting over categories with graph structure, where the dynamics at a vertex depends on its local connectivity structure.

SKIing on Simplices: Kernel Interpolation on the Permutohedral Lattice for Scalable Gaussian Processes

1 code implementation12 Jun 2021 Sanyam Kapoor, Marc Finzi, Ke Alexander Wang, Andrew Gordon Wilson

State-of-the-art methods for scalable Gaussian processes use iterative algorithms, requiring fast matrix vector multiplies (MVMs) with the covariance kernel.

Gaussian Processes

Bayesian Algorithm Execution: Estimating Computable Properties of Black-box Functions Using Mutual Information

1 code implementation19 Apr 2021 Willie Neiswanger, Ke Alexander Wang, Stefano Ermon

Given such an $\mathcal{A}$, and a prior distribution over $f$, we refer to the problem of inferring the output of $\mathcal{A}$ using $T$ evaluations as Bayesian Algorithm Execution (BAX).

Experimental Design Gaussian Processes

Simplifying Hamiltonian and Lagrangian Neural Networks via Explicit Constraints

1 code implementation NeurIPS 2020 Marc Finzi, Ke Alexander Wang, Andrew Gordon Wilson

Reasoning about the physical world requires models that are endowed with the right inductive biases to learn the underlying dynamics.

$DC^2$: A Divide-and-conquer Algorithm for Large-scale Kernel Learning with Application to Clustering

no code implementations16 Nov 2019 Ke Alexander Wang, Xinran Bian, Pan Liu, Donghui Yan

Analysis on $DC^2$ when applied to spectral clustering shows that the loss in clustering accuracy due to data division and reduction is upper bounded by the data approximation error which would vanish with recursive random projections.

Cannot find the paper you are looking for? You can Submit a new open access paper.