Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Daniel Kang

Daniel Kang

Proof: Accelerating Approximate Aggregation Queries with Expensive Predicates


Jul 28, 2021
Daniel Kang, John Guibas, Peter Bailis, Tatsunori Hashimoto, Yi Sun, Matei Zaharia

Figure 1 for Proof: Accelerating Approximate Aggregation Queries with Expensive Predicates

  Access Paper or Ask Questions

Jointly Optimizing Preprocessing and Inference for DNN-based Visual Analytics


Jul 25, 2020
Daniel Kang, Ankit Mathur, Teja Veeramacheneni, Peter Bailis, Matei Zaharia

Figure 1 for Jointly Optimizing Preprocessing and Inference for DNN-based Visual Analytics
Figure 2 for Jointly Optimizing Preprocessing and Inference for DNN-based Visual Analytics
Figure 3 for Jointly Optimizing Preprocessing and Inference for DNN-based Visual Analytics
Figure 4 for Jointly Optimizing Preprocessing and Inference for DNN-based Visual Analytics

  Access Paper or Ask Questions

Improved Natural Language Generation via Loss Truncation


May 01, 2020
Daniel Kang, Tatsunori Hashimoto

Figure 1 for Improved Natural Language Generation via Loss Truncation
Figure 2 for Improved Natural Language Generation via Loss Truncation
Figure 3 for Improved Natural Language Generation via Loss Truncation
Figure 4 for Improved Natural Language Generation via Loss Truncation
* ACL 2020 Camera Ready Submission 
  Access Paper or Ask Questions

Model Assertions for Monitoring and Improving ML Models


Mar 11, 2020
Daniel Kang, Deepti Raghavan, Peter Bailis, Matei Zaharia

Figure 1 for Model Assertions for Monitoring and Improving ML Models
Figure 2 for Model Assertions for Monitoring and Improving ML Models
Figure 3 for Model Assertions for Monitoring and Improving ML Models
Figure 4 for Model Assertions for Monitoring and Improving ML Models
* MLSys 2020 
  Access Paper or Ask Questions

MLPerf Training Benchmark


Oct 30, 2019
Peter Mattson, Christine Cheng, Cody Coleman, Greg Diamos, Paulius Micikevicius, David Patterson, Hanlin Tang, Gu-Yeon Wei, Peter Bailis, Victor Bittorf, David Brooks, Dehao Chen, Debojyoti Dutta, Udit Gupta, Kim Hazelwood, Andrew Hock, Xinyuan Huang, Bill Jia, Daniel Kang, David Kanter, Naveen Kumar, Jeffery Liao, Guokai Ma, Deepak Narayanan, Tayo Oguntebi, Gennady Pekhimenko, Lillian Pentecost, Vijay Janapa Reddi, Taylor Robie, Tom St. John, Carole-Jean Wu, Lingjie Xu, Cliff Young, Matei Zaharia

Figure 1 for MLPerf Training Benchmark
Figure 2 for MLPerf Training Benchmark
Figure 3 for MLPerf Training Benchmark
Figure 4 for MLPerf Training Benchmark

  Access Paper or Ask Questions

Testing Robustness Against Unforeseen Adversaries


Aug 21, 2019
Daniel Kang, Yi Sun, Dan Hendrycks, Tom Brown, Jacob Steinhardt

Figure 1 for Testing Robustness Against Unforeseen Adversaries
Figure 2 for Testing Robustness Against Unforeseen Adversaries
Figure 3 for Testing Robustness Against Unforeseen Adversaries
Figure 4 for Testing Robustness Against Unforeseen Adversaries

  Access Paper or Ask Questions

Willump: A Statistically-Aware End-to-end Optimizer for Machine Learning Inference


Jun 03, 2019
Peter Kraft, Daniel Kang, Deepak Narayanan, Shoumik Palkar, Peter Bailis, Matei Zaharia

Figure 1 for Willump: A Statistically-Aware End-to-end Optimizer for Machine Learning Inference
Figure 2 for Willump: A Statistically-Aware End-to-end Optimizer for Machine Learning Inference
Figure 3 for Willump: A Statistically-Aware End-to-end Optimizer for Machine Learning Inference
Figure 4 for Willump: A Statistically-Aware End-to-end Optimizer for Machine Learning Inference

  Access Paper or Ask Questions

Transfer of Adversarial Robustness Between Perturbation Types


May 03, 2019
Daniel Kang, Yi Sun, Tom Brown, Dan Hendrycks, Jacob Steinhardt

Figure 1 for Transfer of Adversarial Robustness Between Perturbation Types
Figure 2 for Transfer of Adversarial Robustness Between Perturbation Types
Figure 3 for Transfer of Adversarial Robustness Between Perturbation Types
Figure 4 for Transfer of Adversarial Robustness Between Perturbation Types
* 11 pages, 6 figures 
  Access Paper or Ask Questions

Network Offloading Policies for Cloud Robotics: a Learning-based Approach


Feb 15, 2019
Sandeep Chinchali, Apoorva Sharma, James Harrison, Amine Elhafsi, Daniel Kang, Evgenya Pergament, Eyal Cidon, Sachin Katti, Marco Pavone

Figure 1 for Network Offloading Policies for Cloud Robotics: a Learning-based Approach
Figure 2 for Network Offloading Policies for Cloud Robotics: a Learning-based Approach
Figure 3 for Network Offloading Policies for Cloud Robotics: a Learning-based Approach
Figure 4 for Network Offloading Policies for Cloud Robotics: a Learning-based Approach

  Access Paper or Ask Questions

LIT: Block-wise Intermediate Representation Training for Model Compression


Oct 02, 2018
Animesh Koratana, Daniel Kang, Peter Bailis, Matei Zaharia

Figure 1 for LIT: Block-wise Intermediate Representation Training for Model Compression
Figure 2 for LIT: Block-wise Intermediate Representation Training for Model Compression
Figure 3 for LIT: Block-wise Intermediate Representation Training for Model Compression
Figure 4 for LIT: Block-wise Intermediate Representation Training for Model Compression

  Access Paper or Ask Questions

Analysis of DAWNBench, a Time-to-Accuracy Machine Learning Performance Benchmark


Jun 04, 2018
Cody Coleman, Daniel Kang, Deepak Narayanan, Luigi Nardi, Tian Zhao, Jian Zhang, Peter Bailis, Kunle Olukotun, Chris Re, Matei Zaharia

Figure 1 for Analysis of DAWNBench, a Time-to-Accuracy Machine Learning Performance Benchmark
Figure 2 for Analysis of DAWNBench, a Time-to-Accuracy Machine Learning Performance Benchmark
Figure 3 for Analysis of DAWNBench, a Time-to-Accuracy Machine Learning Performance Benchmark
Figure 4 for Analysis of DAWNBench, a Time-to-Accuracy Machine Learning Performance Benchmark

  Access Paper or Ask Questions

NoScope: Optimizing Neural Network Queries over Video at Scale


Aug 08, 2017
Daniel Kang, John Emmons, Firas Abuzaid, Peter Bailis, Matei Zaharia

Figure 1 for NoScope: Optimizing Neural Network Queries over Video at Scale
Figure 2 for NoScope: Optimizing Neural Network Queries over Video at Scale
Figure 3 for NoScope: Optimizing Neural Network Queries over Video at Scale
Figure 4 for NoScope: Optimizing Neural Network Queries over Video at Scale
* PVLDB 2017 
  Access Paper or Ask Questions