Search Results for author: Alex Beatson

Found 9 papers, 4 papers with code

Amortized Finite Element Analysis for Fast PDE-Constrained Optimization

1 code implementation ICML 2020 Tianju Xue, Alex Beatson, Sigrid Adriaenssens , Ryan Adams

Optimizing the parameters of partial differential equations (PDEs), i. e., PDE-constrained optimization (PDE-CO), allows us to model natural systems from observations or perform rational design of structures with complicated mechanical, thermal, or electromagnetic properties.

Meta-PDE: Learning to Solve PDEs Quickly Without a Mesh

no code implementations3 Nov 2022 Tian Qin, Alex Beatson, Deniz Oktay, Nick McGreivy, Ryan P. Adams

Partial differential equations (PDEs) are often computationally challenging to solve, and in many settings many related PDEs must be be solved either at every timestep or for a variety of candidate boundary conditions, parameters, or geometric domains.


Randomized Automatic Differentiation

1 code implementation ICLR 2021 Deniz Oktay, Nick McGreivy, Joshua Aduol, Alex Beatson, Ryan P. Adams

The successes of deep learning, variational inference, and many other fields have been aided by specialized implementations of reverse-mode automatic differentiation (AD) to compute gradients of mega-dimensional objectives.

Stochastic Optimization Variational Inference

SUMO: Unbiased Estimation of Log Marginal Probability for Latent Variable Models

no code implementations ICLR 2020 Yucen Luo, Alex Beatson, Mohammad Norouzi, Jun Zhu, David Duvenaud, Ryan P. Adams, Ricky T. Q. Chen

Standard variational lower bounds used to train latent variable models produce biased estimates of most quantities of interest.

Efficient Optimization of Loops and Limits with Randomized Telescoping Sums

1 code implementation16 May 2019 Alex Beatson, Ryan P. Adams

We consider optimization problems in which the objective requires an inner loop with many steps or is the limit of a sequence of increasingly costly approximations.

Meta-Learning Variational Inference

Amortized Bayesian Meta-Learning

1 code implementation ICLR 2019 Sachin Ravi, Alex Beatson

Meta-learning, or learning-to-learn, has proven to be a successful strategy in attacking problems in supervised learning and reinforcement learning that involve small amounts of data.

Few-Shot Image Classification Few-Shot Learning +1

Continual Learning in Generative Adversarial Nets

no code implementations23 May 2017 Ari Seff, Alex Beatson, Daniel Suo, Han Liu

Developments in deep generative models have allowed for tractable learning of high-dimensional data distributions.

Continual Learning

Blind Attacks on Machine Learners

no code implementations NeurIPS 2016 Alex Beatson, Zhaoran Wang, Han Liu

We study the potential of a “blind attacker” to provably limit a learner’s performance by data injection attack without observing the learner’s training set or any parameter of the distribution from which it is drawn.

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