• Publications
  • Influence
Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks
TLDR
We present an attention-based neural network module, the Set Transformer, specifically designed to model interactions among elements in the input set. Expand
  • 170
  • 39
  • PDF
Set Transformer
TLDR
We present an attention-based neural network module, the Set Transformer, specifically designed to model interactions among elements in the input set. Expand
  • 16
  • 1
  • PDF
Learning to Warm-Start Bayesian Hyperparameter Optimization
Hyperparameter optimization undergoes extensive evaluations of validation errors in order to find its best configuration. Bayesian optimization is now popular for hyperparameter optimization, sinceExpand
  • 12
  • 1
Bayesian Optimization over Sets
TLDR
We propose a Bayesian optimization method over sets, to minimize a black-box function that can take a set as single input. Expand
  • 7
  • 1
  • PDF
Combinatorial 3D Shape Generation via Sequential Assembly
TLDR
We propose a new 3D shape generation algorithm that aims to create such a combinatorial configuration from a set of volumetric primitives. Expand
  • 1
  • 1
  • PDF
Open Set Recognition by Regularising Classifier with Fake Data Generated by Generative Adversarial Networks
TLDR
We present a new method to generate fake data in unknown classes in generative adversarial networks by modelling noisy distribution on feature space of a classifier using marginal denoising autoencoder. Expand
  • 9
  • PDF
On Local Optimizers of Acquisition Functions in Bayesian Optimization
TLDR
We present an analysis on the behavior of local optimizers of acquisition functions, in terms of instantaneous regrets over global optimizers. Expand
  • 11
  • PDF
MxML: Mixture of Meta-Learners for Few-Shot Classification
TLDR
A meta-model is trained on a distribution of similar tasks such that it learns an algorithm that can quickly adapt to a novel task with only a handful of labeled examples. Expand
  • 6
  • PDF
AutoML Challenge: AutoML Framework Using Random Space Partitioning Optimizer
Automated machine learning provides a framework where an algorithm configuration best suited to a particular problem is automatically determined without users’ intervention. In this paper we presentExpand
  • 5
  • PDF
Practical Bayesian Optimization over Sets
TLDR
We propose a practical Bayesian optimization method over sets, to minimize a black-box function that can take a set as a single input. Expand
  • 1
...
1
2
...