78 citations · 187 across the 21 of their papers we have counts for
12 papers · 1 filter
Towards Better Out-of-Distribution Generalization of Neural Algorithmic Reasoning Tasks
Sadegh Mahdavi, Kevin Swersky, Thomas Kipf +3
In this paper, we study the OOD generalization of neural algorithmic reasoning tasks, where the goal is to learn an algorithm (e.g., sorting, breadth-first search, and depth-first…
CUF: Continuous Upsampling Filters
Cristina Vasconcelos, Cengiz Oztireli, Mark Matthews +3
Neural fields have rapidly been adopted for representing 3D signals, but their application to more classical 2D image-processing has been relatively limited. In this paper, we cons…
Analyzing a Caching Model
Leon Sixt, Evan Zheran Liu, Marie Pellat +4
Machine Learning has been successfully applied in systems applications such as memory prefetching and caching, where learned models have been shown to outperform heuristics. Howeve…
Apollo: Transferable Architecture Exploration
Amir Yazdanbakhsh, Christof Angermueller, Berkin Akin +7
The looming end of Moore's Law and ascending use of deep learning drives the design of custom accelerators that are optimized for specific neural architectures. Architecture explor…
Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks
Yujun Yan, Milad Hashemi, Kevin Swersky +2
In node classification tasks, graph convolutional neural networks (GCNs) have demonstrated competitive performance over traditional methods on diverse graph data. However, it is kn…
Oops I Took A Gradient: Scalable Sampling for Discrete Distributions
Will Grathwohl, Kevin Swersky, Milad Hashemi +2
We propose a general and scalable approximate sampling strategy for probabilistic models with discrete variables. Our approach uses gradients of the likelihood function with respec…
Learned Hardware/Software Co-Design of Neural Accelerators
Zhan Shi, Chirag Sakhuja, Milad Hashemi +2
The use of deep learning has grown at an exponential rate, giving rise to numerous specialized hardware and software systems for deep learning. Because the design space of deep lea…
No MCMC for me: Amortized sampling for fast and stable training of energy-based models
Will Grathwohl, Jacob Kelly, Milad Hashemi +3
Energy-Based Models (EBMs) present a flexible and appealing way to represent uncertainty. Despite recent advances, training EBMs on high-dimensional data remains a challenging prob…
An Imitation Learning Approach for Cache Replacement
Evan Zheran Liu, Milad Hashemi, Kevin Swersky +2
Program execution speed critically depends on increasing cache hits, as cache hits are orders of magnitude faster than misses. To increase cache hits, we focus on the problem of ca…
Neural Execution Engines: Learning to Execute Subroutines
Yujun Yan, Kevin Swersky, Danai Koutra +2
A significant effort has been made to train neural networks that replicate algorithmic reasoning, but they often fail to learn the abstract concepts underlying these algorithms. Th…
Learning Execution through Neural Code Fusion
Zhan Shi, Kevin Swersky, Daniel Tarlow +2
As the performance of computer systems stagnates due to the end of Moore's Law, there is a need for new models that can understand and optimize the execution of general purpose cod…
Learning Memory Access Patterns
Milad Hashemi, Kevin Swersky, Jamie A. Smith +5
The explosion in workload complexity and the recent slow-down in Moore's law scaling call for new approaches towards efficient computing. Researchers are now beginning to use recen…