Daniel Kang

发表

DAWNBench : An End-to-End Deep Learning Benchmark and Competition

Kunle Olukotun, Christopher Ré, Jian Zhang, 2017 .

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

Kunle Olukotun, Christopher Ré, Jian Zhang, 2018, ACM SIGOPS Oper. Syst. Rev..

Model Assertions for Monitoring and Improving ML Models pdf

Peter Bailis, Matei Zaharia, Daniel Kang, 2020, MLSys.

Model Assertions for Debugging Machine Learning

Daniel Kang, Peter Bailis, M. Zaharia, 2018 .

Task-agnostic Indexes for Deep Learning-based Queries over Unstructured Data pdf

Peter Bailis, Matei Zaharia, Tatsunori B. Hashimoto, 2020, ArXiv.

MLPerf Training Benchmark pdf

David Patterson, Carole-Jean Wu, Gu-Yeon Wei, 2019, MLSys.

NoScope: Optimizing Deep CNN-Based Queries over Video Streams at Scale

Matei Zaharia, Peter Bailis, John Emmons, 2017, Proc. VLDB Endow..

BlazeIt: Fast Exploratory Video Queries using Neural Networks pdf

Peter Bailis, Matei Zaharia, Daniel Kang, 2018, ArXiv.

Network offloading policies for cloud robotics: a learning-based approach pdf

Marco Pavone, Apoorva Sharma, Sandeep Chinchali, 2019, Autonomous Robots.

Network offloading policies for cloud robotics: a learning-based approach

Marco Pavone, Sandeep Chinchali, Sachin Katti, 2021, Auton. Robots.

NoScope: Optimizing Deep CNN-Based Queries over Video Streams at Scale

Peter Bailis, Matei Zaharia, John Emmons, 2017, Proc. VLDB Endow..

BlazeIt: Optimizing Declarative Aggregation and Limit Queries for Neural Network-Based Video Analytics

Peter Bailis, Matei Zaharia, Daniel Kang, 2018, Proc. VLDB Endow..

Approximate selection with guarantees using proxies

Peter Bailis, Matei Zaharia, Tatsunori B. Hashimoto, 2020, Proc. VLDB Endow..

Coherence Time ! = # ! = $ Query Cloud SVM Classifier Robot Model FaceNet Embed

Daniel Kang, M. Pavone, J. Harrison, 2022 .

Analysis of the Time-To-Accuracy Metric and Entries in the DAWNBench Deep Learning Benchmark

Cody A. Coleman, D. Narayanan, Daniel Kang, 2018 .

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

D. Narayanan, Daniel Kang, M. Zaharia, 2019, 1906.01974.

Scaling up Trustless DNN Inference with Zero-Knowledge Proofs

Tatsunori B. Hashimoto, Daniel Kang, I. Stoica, 2022, ArXiv.

ZK-IMG: Attested Images via Zero-Knowledge Proofs to Fight Disinformation

Tatsunori B. Hashimoto, Daniel Kang, Yi Sun, 2022, ArXiv.

TASTI: Semantic Indexes for Machine Learning-based Queries over Unstructured Data

Daniel Kang, M. Zaharia, John Guibas, 2020, SIGMOD Conference.

Approximate selection with guarantees using proxies

Tatsunori B. Hashimoto, Daniel Kang, M. Zaharia, 2020, Proc. VLDB Endow..

LIT: Learned Intermediate Representation Training for Model Compression

Peter Bailis, Matei Zaharia, Daniel Kang, 2019, ICML.

Accelerating Approximate Aggregation Queries with Expensive Predicates

Daniel Kang, John Guibas, Daniel Kang, 2021, Proc. VLDB Endow..

Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Carlos Guestrin, Daniel Kang, M. Zaharia, 2023, ArXiv.

Optimizing Video Analytics with Declarative Model Relationships

Daniel Kang, M. Zaharia, Francisco Romero, 2022, Proc. VLDB Endow..

MLPerf Training Benchmark

Cody A. Coleman, D. Narayanan, Daniel Kang, 2019, MLSys.

BlazeIt: Optimizing Declarative Aggregation and Limit Queries for Neural Network-Based Video Analytics

Daniel Kang, M. Zaharia, Peter D. Bailis, 2018, Proc. VLDB Endow..

Challenges and Opportunities in DNN-Based Video Analytics: A Demonstration of the BlazeIt Video Query Engine

Peter Bailis, Matei Zaharia, Daniel Kang, 2019, CIDR.

Finding Label and Model Errors in Perception Data With Learned Observation Assertions

Nikos Arechiga, Peter Bailis, Matei Zaharia, 2022, SIGMOD Conference.

Testing Robustness Against Unforeseen Adversaries pdf

Yi Sun, Dan Hendrycks, Daniel Kang, 2019, ArXiv.

VIVA: An End-to-End System for Interactive Video Analytics

Daniel Kang, M. Zaharia, Francisco Romero, 2022, CIDR.

Transfer of Adversarial Robustness Between Perturbation Types pdf

Yi Sun, Tom Brown, Dan Hendrycks, 2019, ArXiv.

Improved Natural Language Generation via Loss Truncation pdf

Tatsunori B. Hashimoto, Daniel Kang, Tatsunori Hashimoto, 2020, ACL.

Finding Label Errors in Autonomous Vehicle Data With Learned Observation Assertions

Daniel Kang, M. Zaharia, Sudeep Pillai, 2021 .

Optimizing Deep CNN-Based Queries over Video Streams at Scale

Daniel Kang, M. Zaharia, Firas Abuzaid, 2017, VLDB 2017.

Testing Robustness Against Unforeseen Adversaries.

Tom B. Brown, Daniel Kang, J. Steinhardt, 2019 .

Jointly Optimizing Preprocessing and Inference for DNN-based Visual Analytics pdf

Peter Bailis, Matei Zaharia, Daniel Kang, 2020, Proc. VLDB Endow..

Identifying and Mitigating the Security Risks of Generative AI

Nicholas Carlini, D. Song, Daniel Kang, 2023, ArXiv.

Testing Robustness Against Unforeseen Adversaries

Daniel Kang, J. Steinhardt, Xuwang Yin, 2019, 1908.08016.

Identifying and Mitigating the Security Risks of Generative AI

Nicholas Carlini, D. Song, Daniel Kang, 2023, Found. Trends Priv. Secur..

Dias: Dynamic Rewriting of Pandas Code

Daniel Kang, Charith Mendis, Stefanos Baziotis, 2023, ArXiv.

Predictive Models for Determining If and When to Display Online Lead Forms

Tomonori Honda, Carlos Ruiz, Daniel Kang, 2014, AAAI.