Подписаться
James Diffenderfer
James Diffenderfer
University of Florida, Lawrence Livermore National Laboratory
Подтвержден адрес электронной почты в домене llnl.gov
Название
Процитировано
Процитировано
Год
Multi-prize lottery ticket hypothesis: Finding accurate binary neural networks by pruning a randomly weighted network
J Diffenderfer, B Kailkhura
arXiv preprint arXiv:2103.09377, 2021
1072021
Error analysis of zfp compression for floating-point data
J Diffenderfer, AL Fox, JA Hittinger, G Sanders, PG Lindstrom
SIAM Journal on Scientific Computing 41 (3), A1867-A1898, 2019
882019
A winning hand: Compressing deep networks can improve out-of-distribution robustness
J Diffenderfer, B Bartoldson, S Chaganti, J Zhang, B Kailkhura
Advances in neural information processing systems 34, 664-676, 2021
792021
Deepzero: Scaling up zeroth-order optimization for deep model training
A Chen, Y Zhang, J Jia, J Diffenderfer, J Liu, K Parasyris, Y Zhang, ...
arXiv preprint arXiv:2310.02025, 2023
352023
Gtbench: Uncovering the strategic reasoning limitations of llms via game-theoretic evaluations
J Duan, R Zhang, J Diffenderfer, B Kailkhura, L Sun, E Stengel-Eskin, ...
arXiv preprint arXiv:2402.12348, 2024
332024
Soul: Unlocking the power of second-order optimization for llm unlearning
J Jia, Y Zhang, Y Zhang, J Liu, B Runwal, J Diffenderfer, B Kailkhura, ...
arXiv preprint arXiv:2404.18239, 2024
242024
Stability analysis of inline ZFP compression for floating-point data in iterative methods
A Fox, J Diffenderfer, J Hittinger, G Sanders, P Lindstrom
SIAM Journal on Scientific Computing 42 (5), A2701-A2730, 2020
242020
Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studies
BR Bartoldson, J Diffenderfer, K Parasyris, B Kailkhura
arXiv preprint arXiv:2404.09349, 2024
172024
HPAC: evaluating approximate computing techniques on HPC OpenMP applications
K Parasyris, G Georgakoudis, H Menon, J Diffenderfer, I Laguna, ...
Proceedings of the International Conference for High Performance Computing …, 2021
162021
Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression
J Hong, J Duan, C Zhang, Z Li, C Xie, K Lieberman, J Diffenderfer, ...
arXiv preprint arXiv:2403.15447, 2024
142024
Algorithm 1035: a gradient-based implementation of the polyhedral active set algorithm
WW Hager, H Zhang
ACM Transactions on Mathematical Software 49 (2), 1-13, 2023
82023
Approximate computing through the lens of uncertainty quantification
K Parasyris, J Diffenderfer, H Menon, I Laguna, J Vanover, R Vogt, ...
SC22: International Conference for High Performance Computing, Networking …, 2022
72022
Benchmarking test-time unsupervised deep neural network adaptation on edge devices
K Bhardwaj, J Diffenderfer, B Kailkhura, M Gokhale
2022 IEEE International Symposium on Performance Analysis of Systems and …, 2022
72022
ReTA: Recursively Thinking Ahead to Improve the Strategic Reasoning of Large Language Models
J Duan, S Wang, J Diffenderfer, L Sun, T Chen, B Kailkhura, K Xu
Proceedings of the 2024 Conference of the North American Chapter of the …, 2024
62024
A comparative study of predicting high entropy alloy phase fractions with traditional machine learning and deep neural networks
S Liu, B Bocklund, J Diffenderfer, S Chaganti, B Kailkhura, SK McCall, ...
npj Computational Materials 10 (1), 172, 2024
52024
Uncovering the strategic reasoning limitations of llms via game-theoretic evaluations
J Duan, R Zhang, J Diffenderfer, B Kailkhura, L Sun, E Stengel-Eskin, ...
arXiv preprint arXiv:2402.12348, 2024
52024
Unsupervised test-time adaptation of deep neural networks at the edge: a case study
K Bhardwaj, J Diffenderfer, B Kailkhura, M Gokhale
2022 Design, Automation & Test in Europe Conference & Exhibition (DATE), 412-417, 2022
52022
QDOT: Quantized dot product kernel for approximate high-performance computing
J Diffenderfer, D Osei-Kuffuor, H Menon
arXiv preprint arXiv:2105.00115, 2021
52021
Variable precision computing
JAF Hittinger, PG Lindstrom, H Bhatia, PT Bremer, DM Copeland, ...
Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States), 2019
52019
Zeroth-order sciml: Non-intrusive integration of scientific software with deep learning
I Tsaknakis, B Kailkhura, S Liu, D Loveland, J Diffenderfer, AM Hiszpanski, ...
arXiv preprint arXiv:2206.02785, 2022
42022
В данный момент система не может выполнить эту операцию. Повторите попытку позднее.
Статьи 1–20