"Understanding Deep Learning (Still) Requires Rethinking Generalization," Chiyuan Zhang, et al., brings a fundamental new theoretical challenge: Why don't today's...Sanjeev Arora From Communications of the ACM | March 2021
In this work, we presented a simple experimental framework for interrogating purported measures of generalization.
Chiyuan Zhang, Samy Bengio, Moritz Hardt, Benjamin Recht, Oriol Vinyals From Communications of the ACM | March 2021
How to produce a convolutional neural net that is small enough to run on a mobile device, and accurate enough to be worth using? The strategies in "Enabling AI...David Alexander Forsyth From Communications of the ACM | December 2020
We present a novel approach to running state-of-the-art AI algorithms in edge devices, and propose two efficient approximations to standard convolutional neural...Mohammad Rastegari, Vicente Ordonez, Joseph Redmon, Ali Farhadi From Communications of the ACM | December 2020
The key insight of the "Generative Adversarial Networks," by Ian Goodfellow et al., is to learn a generative model's loss function at the same time as learning...Alexei A. Efros, Aaron Hertzmann From Communications of the ACM | November 2020
In this overview paper, we describe one particular approach to unsupervised learning via generative modeling called generative adversarial networks. We briefly...Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio From Communications of the ACM | November 2020
Magellan's key insight is that a successful entity matching system must offer a versatile system building paradigm for entity matching that can be easily adapted...Wang-Chiew Tan From Communications of the ACM | August 2020
Entity matching can be viewed as a special class of data science problems and thus can benefit from system building ideas in data science.
AnHai Doan, Pradap Konda, Paul Suganthan G. C., Yash Govind, Derek Paulsen, Kaushik Chandrasekhar, Philip Martinkus, Matthew Christie From Communications of the ACM | August 2020
"Data-Driven Algorithm Design," by Rishi Gupta and Tim Roughgarden, addresses the issue that the best algorithm to use for many problems depends on what the input...Avrim Blum From Communications of the ACM | June 2020
The envy-free cake-cutting problem stood its ground for two decades, until it was cracked by Aziz and Mackenzie. Their solution is presented in "A Bounded and Envy...Ariel D. Procaccia From Communications of the ACM | April 2020
We report on our algorithm that resolved the well-studied cake cutting problem in which the goal is to find an envy-free allocation of a divisible resource based...Haris Aziz, Simon Mackenzie From Communications of the ACM | April 2020
Instead of handing trace records off to a collector for long-term storage and future processing, the system described in "Pivot Tracing: Dynamic Causal Monitoring...Rebecca Isaacs From Communications of the ACM | March 2020
This paper presents Pivot Tracing, a monitoring framework for distributed systems, which addresses the limitations of today's monitoring and diagnosis tools by...Jonathan Mace, Ryan Roelke, Rodrigo Fonseca From Communications of the ACM | March 2020
"Automating Visual Privacy Protection Using a Smart LED," presents a new technique to address the issue of cameras capturing proprietary or private information—it...Marco Gruteser From Communications of the ACM | February 2020
We introduce LiShield, which automatically protects a physical scene against photographing, by illuminating it with smart LEDs flickering in specialized waveforms...Shilin Zhu, Chi Zhang, Xinyu Zhang From Communications of the ACM | February 2020
OpenPiton research is one of the watershed moments in the fundamental shift toward the construction of an open source ecosystem for implementing prototype chips...Michael B. Taylor From Communications of the ACM | December 2019
We present OpenPiton, an open source framework for building scalable architecture research prototypes from one core to 500 million cores.
Jonathan Balkind, Michael McKeown, Yaosheng Fu, Tri Nguyen, Yanqi Zhou, Alexey Lavrov, Mohammad Shahrad, Adi Fuchs, Samuel Payne, Xiaohua Liang, Matthew Matl, David Wentzlaff From Communications of the ACM | December 2019
DeepXplore brings a software testing perspective to deep neural networks and, in doing so, creates the opportunity for enormous amounts of follow-on work in several...David G. Andersen From Communications of the ACM | November 2019
We design, implement, and evaluate DeepXplore, the first white-box framework for systematically testing real-world deep learning systems.
Kexin Pei, Yinzhi Cao, Junfeng Yang, Suman Jana From Communications of the ACM | November 2019