b'Kevin Swersky'

research

∙ 04/21/2023

Low-Variance Gradient Estimation in Unrolled Computation Graphs with ES-Single

We propose an evolution strategies-based algorithm for estimating gradie...

0 Paul Vicol, et al. ∙

research

∙ 10/13/2022

CUF: Continuous Upsampling Filters

Neural fields have rapidly been adopted for representing 3D signals, but...

0 Cristina Vasconcelos, et al. ∙

research

∙ 08/09/2022

Learning to Improve Code Efficiency

Improvements in the performance of computing systems, driven by Moore's ...

0 Binghong Chen, et al. ∙

research

∙ 07/07/2022

Pre-training helps Bayesian optimization too

Bayesian optimization (BO) has become a popular strategy for global opti...

17 Zi Wang, et al. ∙

research

∙ 10/20/2021

Data-Driven Offline Optimization For Architecting Hardware Accelerators

Industry has gradually moved towards application-specific hardware accel...

7 Aviral Kumar, et al. ∙

research

∙ 09/16/2021

Automatic prior selection for meta Bayesian optimization with a case study on tuning deep neural network optimizers

The performance of deep neural networks can be highly sensitive to the c...

9 Zi Wang, et al. ∙

research

∙ 02/12/2021

Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks

Most graph neural networks (GNN) perform poorly in graphs where neighbor...

0 Yujun Yan, et al. ∙

research

∙ 02/08/2021

Oops I Took A Gradient: Scalable Sampling for Discrete Distributions

We propose a general and scalable approximate sampling strategy for prob...

2 Will Grathwohl, et al. ∙

research

∙ 02/02/2021

Apollo: Transferable Architecture Exploration

The looming end of Moore's Law and ascending use of deep learning drives...

6 Amir Yazdanbakhsh, et al. ∙

research

∙ 12/18/2020

Human 3D keypoints via spatial uncertainty modeling

We introduce a technique for 3D human keypoint estimation that directly ...

5 Francis Williams, et al. ∙

research

∙ 10/08/2020

No MCMC for me: Amortized sampling for fast and stable training of energy-based models

Energy-Based Models (EBMs) present a flexible and appealing way to repre...

6 Will Grathwohl, et al. ∙

research

∙ 10/05/2020

Learned Hardware/Software Co-Design of Neural Accelerators

The use of deep learning has grown at an exponential rate, giving rise t...

14 Zhan Shi, et al. ∙

research

∙ 07/31/2020

Optimizing Long-term Social Welfare in Recommender Systems: A Constrained Matching Approach

Most recommender systems (RS) research assumes that a user's utility can...

4 Martin Mladenov, et al. ∙

research

∙ 06/29/2020

An Imitation Learning Approach for Cache Replacement

Program execution speed critically depends on increasing cache hits, as ...

8 Evan Zheran Liu, et al. ∙

research

∙ 06/17/2020

Big Self-Supervised Models are Strong Semi-Supervised Learners

One paradigm for learning from few labeled examples while making best us...

6 Ting Chen, et al. ∙

research

∙ 06/15/2020

Neural Execution Engines: Learning to Execute Subroutines

A significant effort has been made to train neural networks that replica...

5 Yujun Yan, et al. ∙

research

∙ 02/18/2020

SentenceMIM: A Latent Variable Language Model

We introduce sentenceMIM, a probabilistic auto-encoder for language mode...

0 Micha Livne, et al. ∙

research

∙ 12/06/2019

Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One

We propose to reinterpret a standard discriminative classifier of p(y|x)...

19 Will Grathwohl, et al. ∙

research

∙ 10/08/2019

MIM: Mutual Information Machine

We introduce the Mutual Information Machine (MIM), an autoencoder model ...

47 Micha Livne, et al. ∙

research

∙ 10/04/2019

High Mutual Information in Representation Learning with Symmetric Variational Inference

We introduce the Mutual Information Machine (MIM), a novel formulation o...

18 Micha Livne, et al. ∙

research

∙ 06/17/2019

Learning Execution through Neural Code Fusion

As the performance of computer systems stagnates due to the end of Moore...

1 Zhan Shi, et al. ∙

research

∙ 06/06/2019

Flexibly Fair Representation Learning by Disentanglement

We consider the problem of learning representations that achieve group a...

4 Elliot Creager, et al. ∙

research

∙ 05/31/2019

Learning Sparse Networks Using Targeted Dropout

Neural networks are easier to optimise when they have many more weights ...

26 Aidan N. Gomez, et al. ∙

research

∙ 05/30/2019

Graph Normalizing Flows

We introduce graph normalizing flows: a new, reversible graph neural net...

9 Jenny Liu, et al. ∙

research

∙ 04/04/2019

Neural Networks for Modeling Source Code Edits

Programming languages are emerging as a challenging and interesting doma...

2 Rui Zhao, et al. ∙

research

∙ 03/07/2019

Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples

Few-shot classification refers to learning a classifier for new classes ...

43 Eleni Triantafillou, et al. ∙

research

∙ 03/06/2018

Learning Memory Access Patterns

The explosion in workload complexity and the recent slow-down in Moore's...

0 Milad Hashemi, et al. ∙

research

∙ 03/02/2018

Meta-Learning for Semi-Supervised Few-Shot Classification

In few-shot classification, we are interested in learning algorithms tha...

0 Mengye Ren, et al. ∙

research

∙ 06/16/2017

An online sequence-to-sequence model for noisy speech recognition

Generative models have long been the dominant approach for speech recogn...

0 Chung-Cheng Chiu, et al. ∙

research

∙ 05/16/2017

Learning Hard Alignments with Variational Inference

There has recently been significant interest in hard attention models fo...

0 Dieterich Lawson, et al. ∙

research

∙ 03/15/2017

Prototypical Networks for Few-shot Learning

We propose prototypical networks for the problem of few-shot classificat...

0 Jake Snell, et al. ∙

research

∙ 11/03/2015

The Variational Fair Autoencoder

We investigate the problem of learning representations that are invarian...

0 Christos Louizos, et al. ∙

research

∙ 06/01/2015

Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptions

One of the main challenges in Zero-Shot Learning of visual categories is...

0 Jimmy Ba, et al. ∙

research

∙ 02/19/2015

Scalable Bayesian Optimization Using Deep Neural Networks

Bayesian optimization is an effective methodology for the global optimiz...

0 Jasper Snoek, et al. ∙

research

∙ 02/10/2015

Generative Moment Matching Networks

We consider the problem of learning deep generative models from data. We...

0 Yujia Li, et al. ∙

research

∙ 12/17/2014

Learning unbiased features

A key element in transfer learning is representation learning; if repres...

0 Yujia Li, et al. ∙

research

∙ 02/05/2014

Input Warping for Bayesian Optimization of Non-stationary Functions

Bayesian optimization has proven to be a highly effective methodology fo...

0 Jasper Snoek, et al. ∙

research

∙ 10/16/2012

Fast Exact Inference for Recursive Cardinality Models

Cardinality potentials are a generally useful class of high order potent...

0 Daniel Tarlow, et al. ∙

research

∙ 06/27/2012

Estimating the Hessian by Back-propagating Curvature

In this work we develop Curvature Propagation (CP), a general technique ...

0 James Martens, et al. ∙

Kevin Swersky

Featured Co-authors