Amir Gholami

120 papers A* 25A 5B 1C 3Misc 2Journal 77Unranked 7
YearRankTypeTitle / Venue / Authors
2026 J jnl
Agentic Test-Time Scaling for WebAgents.
CoRR
Nicholas Lee, Lutfi Eren Erdogan, Chris Joseph John, Surya Krishnapillai, Michael W. Mahoney, Kurt Keutzer, Amir Gholami
2026 J jnl
On Neural Scaling Laws for Weather Emulation through Continual Training.
CoRR
Shashank Subramanian, Alexander Kiefer, Arnur Nigmetov, Amir Gholami, Dmitriy Morozov, Michael W. Mahoney
2026 J jnl
Residual Context Diffusion Language Models.
CoRR
Yuezhou Hu, Harman Singh, Monishwaran Maheswaran, Haocheng Xi, Coleman Hooper, Jintao Zhang, Aditya Tomar, Michael W. Mahoney, Sewon Min, Mehrdad Farajtabar, Kurt Keutzer, Amir Gholami, Chenfeng Xu
2026 J jnl
Reward Under Attack: Analyzing the Robustness and Hackability of Process Reward Models.
CoRR
Rishabh Tiwari, Aditya Tomar, Udbhav Bamba, Monishwaran Maheswaran, Heng Yang, Michael W. Mahoney, Kurt Keutzer, Amir Gholami
2025 J jnl
Arbitrage: Efficient Reasoning via Advantage-Aware Speculation.
CoRR
Monishwaran Maheswaran, Rishabh Tiwari, Yuezhou Hu, Kerem Dilmen, Coleman Hooper, Haocheng Xi, Nicholas Lee, Mehrdad Farajtabar, Michael W. Mahoney, Kurt Keutzer, Amir Gholami
2025 J jnl
Beyond Next-Token Prediction: A Performance Characterization of Diffusion versus Autoregressive Language Models.
CoRR
Minseo Kim, Coleman Hooper, Aditya Tomar, Chenfeng Xu, Mehrdad Farajtabar, Michael W. Mahoney, Kurt Keutzer, Amir Gholami
2025 J jnl
CDLM: Consistency Diffusion Language Models For Faster Sampling.
CoRR
Minseo Kim, Chenfeng Xu, Coleman Hooper, Harman Singh, Ben Athiwaratkun, Ce Zhang, Kurt Keutzer, Amir Gholami
2025 J jnl
ETS: Efficient Tree Search for Inference-Time Scaling.
CoRR
Coleman Hooper, Sehoon Kim, Suhong Moon, Kerem Dilmen, Monishwaran Maheswaran, Nicholas Lee, Michael W. Mahoney, Yakun Sophia Shao, Kurt Keutzer, Amir Gholami
2025 J jnl
Multipole Attention for Efficient Long Context Reasoning.
CoRR
Coleman Hooper, Sebastian Zhao, Luca Manolache, Sehoon Kim, Michael W. Mahoney, Yakun Sophia Shao, Kurt Keutzer, Amir Gholami
2025 A* conf
Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks.
ICML
Lutfi Eren Erdogan, Nicholas Lee, Sehoon Kim, Suhong Moon, Hiroki Furuta, Gopala Anumanchipalli, Kurt Keutzer, Amir Gholami
2025 J jnl
Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks.
CoRR
Lutfi Eren Erdogan, Nicholas Lee, Sehoon Kim, Suhong Moon, Hiroki Furuta, Gopala Anumanchipalli, Kurt Keutzer, Amir Gholami
2025 A* conf
QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache.
ICML
Rishabh Tiwari, Haocheng Xi, Aditya Tomar, Coleman Richard Charles Hooper, Sehoon Kim, Maxwell Horton, Mahyar Najibi, Michael W. Mahoney, Kurt Keutzer, Amir Gholami
2025 J jnl
QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache.
CoRR
Rishabh Tiwari, Haocheng Xi, Aditya Tomar, Coleman Hooper, Sehoon Kim, Maxwell Horton, Mahyar Najibi, Michael W. Mahoney, Kurt Keutzer, Amir Gholami
2025 J jnl
SciML Agents: Write the Solver, Not the Solution.
CoRR
Saarth Gaonkar, Xiang Zheng, Haocheng Xi, Rishabh Tiwari, Kurt Keutzer, Dmitriy Morozov, Michael W. Mahoney, Amir Gholami
2025 — conf
Squeezed Attention: Accelerating Long Context Length LLM Inference.
ACL (1)
Coleman Richard Charles Hooper, Sehoon Kim, Hiva Mohammadzadeh, Monishwaran Maheswaran, Sebastian Zhao, June Paik, Michael W. Mahoney, Kurt Keutzer, Amir Gholami
2025 J jnl
XQuant: Breaking the Memory Wall for LLM Inference with KV Cache Rematerialization.
CoRR
Aditya Tomar, Coleman Hooper, Minjae Lee, Haocheng Xi, Rishabh Tiwari, Wonjun Kang, Luca Manolache, Michael W. Mahoney, Kurt Keutzer, Amir Gholami
2024 J jnl
AI and Memory Wall.
CoRR
Amir Gholami, Zhewei Yao, Sehoon Kim, Coleman Hooper, Michael W. Mahoney, Kurt Keutzer
2024 J jnl
AI and Memory Wall.
IEEE Micro
Amir Gholami, Zhewei Yao, Sehoon Kim, Coleman Hooper, Michael W. Mahoney, Kurt Keutzer
2024 A* conf
An LLM Compiler for Parallel Function Calling.
ICML
Sehoon Kim, Suhong Moon, Ryan Tabrizi, Nicholas Lee, Michael W. Mahoney, Kurt Keutzer, Amir Gholami
2024 J jnl
Characterizing Prompt Compression Methods for Long Context Inference.
CoRR
Siddharth Jha, Lutfi Eren Erdogan, Sehoon Kim, Kurt Keutzer, Amir Gholami
2024 J jnl
Corrigendum: Applications and techniques for fast machine learning in science.
Frontiers Big Data
Allison McCarn Deiana, Nhan Tran, Joshua Agar, Michaela Blott, Giuseppe Di Guglielmo, Javier M. Duarte, Philip C. Harris, Scott Hauck, Mia Liu, Mark S. Neubauer, Jennifer Ngadiuba, Seda Ogrenci-Memik, Maurizio Pierini, Thea Aarrestad, Steffen Bähr, Jürgen Becker, Anne-Sophie Berthold, Richard J. Bonventre, Tomás E. Müller-Bravo, Markus Diefenthaler, Zhen Dong, Nick Fritzsche, Amir Gholami, Ekaterina Govorkova, Dongning Guo, Kyle J. Hazelwood, Christian Herwig, Babar Khan, Sehoon Kim, Thomas Klijnsma, Yaling Liu, Kin Ho Lo, Tri Nguyen, Gianantonio Pezzullo, Seyedramin Rasoulinezhad, Ryan A. Rivera, Kate Scholberg, Justin Selig, Sougata Sen, Dmitri Strukov, William Tang, Savannah Thais, Kai Lukas Unger, Ricardo Vilalta, Belinavon Krosigk, Shen Wang, Thomas K. Warburton
2024 J jnl
Detection and Classification of Anomalies in Power Distribution System Using Outlier Filtered Weighted Least Square.
IEEE Trans. Ind. Informatics
Amir Gholami, Ashutosh Tiwari, Chuan Qin, Sanjeev Pannala, Anurag Srivastava, Roshan Sharma, Shikhar Pandey, Farnoosh Rahmatian
2024 J jnl
Efficient and Scalable Estimation of Tool Representations in Vector Space.
CoRR
Suhong Moon, Siddharth Jha, Lutfi Eren Erdogan, Sehoon Kim, Woosang Lim, Kurt Keutzer, Amir Gholami
2024 A* conf
KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization.
NeurIPS
Coleman Hooper, Sehoon Kim, Hiva Mohammadzadeh, Michael W. Mahoney, Yakun Sophia Shao, Kurt Keutzer, Amir Gholami
2024 J jnl
KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization.
CoRR
Coleman Hooper, Sehoon Kim, Hiva Mohammadzadeh, Michael W. Mahoney, Yakun Sophia Shao, Kurt Keutzer, Amir Gholami
2024 — conf
LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement.
ACL (Findings)
Nicholas Lee, Thanakul Wattanawong, Sehoon Kim, Karttikeya Mangalam, Sheng Shen, Gopala Anumanchipalli, Michael W. Mahoney, Kurt Keutzer, Amir Gholami
2024 J jnl
LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement.
CoRR
Nicholas Lee, Thanakul Wattanawong, Sehoon Kim, Karttikeya Mangalam, Sheng Shen, Gopala Anumanchipalli, Michael W. Mahoney, Kurt Keutzer, Amir Gholami
2024 J jnl
Multi-Source Data Aggregation and Real-Time Anomaly Classification and Localization in Power Distribution Systems.
IEEE Trans. Smart Grid
Mehdi Ganjkhani, Amir Gholami, Jairo Giraldo, Anurag K. Srivastava, Masood Parvania
2024 J jnl
ORCA: Outage Root Cause Analysis in DER-Rich Power Distribution System Using Data Fusion, Hierarchical Clustering and FP-Growth Rule Mining.
IEEE Trans. Smart Grid
Amir Gholami, Anurag Srivastava
2024 Misc conf
Reliable edge machine learning hardware for scientific applications.
VTS
Tommaso Baldi, Javier Campos, Benjamin Hawks, Jennifer Ngadiuba, Nhan Tran, Daniel Diaz, Javier M. Duarte, Ryan Kastner, Andres Meza, Melissa Quinnan, Olivia Weng, Caleb Geniesse, Amir Gholami, Michael W. Mahoney, Vladimir Loncar, Philip C. Harris, Joshua Agar, Shuyu Qin
2024 J jnl
Reliable edge machine learning hardware for scientific applications.
CoRR
Tommaso Baldi, Javier Campos, Benjamin Hawks, Jennifer Ngadiuba, Nhan Tran, Daniel Diaz, Javier M. Duarte, Ryan Kastner, Andres Meza, Melissa Quinnan, Olivia Weng, Caleb Geniesse, Amir Gholami, Michael W. Mahoney, Vladimir Loncar, Philip C. Harris, Joshua Agar, Shuyu Qin
2024 J jnl
Spatio-Temporal Deep Graph Network for Event Detection, Localization, and Classification in Cyber-Physical Electric Distribution System.
IEEE Trans. Ind. Informatics
Arman Ahmed, Sagnik Basumallik, Amir Gholami, Sajan K. Sadanandan, Mohammad Hossein Namaki, Anurag K. Srivastava, Yinghui Wu
2024 A* conf
SqueezeLLM: Dense-and-Sparse Quantization.
ICML
Sehoon Kim, Coleman Hooper, Amir Gholami, Zhen Dong, Xiuyu Li, Sheng Shen, Michael W. Mahoney, Kurt Keutzer
2024 J jnl
Squeezed Attention: Accelerating Long Context Length LLM Inference.
CoRR
Coleman Hooper, Sehoon Kim, Hiva Mohammadzadeh, Monishwaran Maheswaran, June Paik, Michael W. Mahoney, Kurt Keutzer, Amir Gholami
2024 — conf
TinyAgent: Function Calling at the Edge.
EMNLP (System Demonstrations)
Lutfi Eren Erdogan, Nicholas Lee, Siddharth Jha, Sehoon Kim, Ryan Tabrizi, Suhong Moon, Coleman Richard Charles Hooper, Gopala Anumanchipalli, Kurt Keutzer, Amir Gholami
2024 J jnl
TinyAgent: Function Calling at the Edge.
CoRR
Lutfi Eren Erdogan, Nicholas Lee, Siddharth Jha, Sehoon Kim, Ryan Tabrizi, Suhong Moon, Coleman Hooper, Gopala Anumanchipalli, Kurt Keutzer, Amir Gholami
2023 A conf
Adaptive Self-Supervision Algorithms for Physics-Informed Neural Networks.
ECAI
Shashank Subramanian, Robert M. Kirby, Michael W. Mahoney, Amir Gholami
2023 J jnl
An LLM Compiler for Parallel Function Calling.
CoRR
Sehoon Kim, Suhong Moon, Ryan Tabrizi, Nicholas Lee, Michael W. Mahoney, Kurt Keutzer, Amir Gholami
2023 J jnl
Big Little Transformer Decoder.
CoRR
Sehoon Kim, Karttikeya Mangalam, Jitendra Malik, Michael W. Mahoney, Amir Gholami, Kurt Keutzer
2023 J jnl
End-to-end codesign of Hessian-aware quantized neural networks for FPGAs and ASICs.
CoRR
Javier Campos, Zhen Dong, Javier M. Duarte, Amir Gholami, Michael W. Mahoney, Jovan Mitrevski, Nhan Tran
2023 J jnl
Full Stack Optimization of Transformer Inference: a Survey.
CoRR
Sehoon Kim, Coleman Hooper, Thanakul Wattanawong, Minwoo Kang, Ruohan Yan, Hasan Genc, Grace Dinh, Qijing Huang, Kurt Keutzer, Michael W. Mahoney, Yakun Sophia Shao, Amir Gholami
2023 J jnl
SPEED: Speculative Pipelined Execution for Efficient Decoding.
CoRR
Coleman Hooper, Sehoon Kim, Hiva Mohammadzadeh, Hasan Genc, Kurt Keutzer, Amir Gholami, Yakun Sophia Shao
2023 A* conf
Speculative Decoding with Big Little Decoder.
NeurIPS
Sehoon Kim, Karttikeya Mangalam, Suhong Moon, Jitendra Malik, Michael W. Mahoney, Amir Gholami, Kurt Keutzer
2023 J jnl
SqueezeLLM: Dense-and-Sparse Quantization.
CoRR
Sehoon Kim, Coleman Hooper, Amir Gholami, Zhen Dong, Xiuyu Li, Sheng Shen, Michael W. Mahoney, Kurt Keutzer
2023 A* conf
Towards Foundation Models for Scientific Machine Learning: Characterizing Scaling and Transfer Behavior.
NeurIPS
Shashank Subramanian, Peter Harrington, Kurt Keutzer, Wahid Bhimji, Dmitriy Morozov, Michael W. Mahoney, Amir Gholami
2023 J jnl
Towards Foundation Models for Scientific Machine Learning: Characterizing Scaling and Transfer Behavior.
CoRR
Shashank Subramanian, Peter Harrington, Kurt Keutzer, Wahid Bhimji, Dmitriy Morozov, Michael W. Mahoney, Amir Gholami
2022 A* conf
A Fast Post-Training Pruning Framework for Transformers.
NeurIPS
Woosuk Kwon, Sehoon Kim, Michael W. Mahoney, Joseph Hassoun, Kurt Keutzer, Amir Gholami
2022 J jnl
A Fast Post-Training Pruning Framework for Transformers.
CoRR
Woosuk Kwon, Sehoon Kim, Michael W. Mahoney, Joseph Hassoun, Kurt Keutzer, Amir Gholami
2022 J jnl
Adaptive Self-supervision Algorithms for Physics-informed Neural Networks.
CoRR
Shashank Subramanian, Robert M. Kirby, Michael W. Mahoney, Amir Gholami
2022 J jnl
Applications and Techniques for Fast Machine Learning in Science.
Frontiers Big Data
Allison McCarn Deiana, Nhan Tran, Joshua Agar, Michaela Blott, Giuseppe Di Guglielmo, Javier M. Duarte, Philip C. Harris, Scott Hauck, Mia Liu, Mark S. Neubauer, Jennifer Ngadiuba, Seda Ogrenci Memik, Maurizio Pierini, Thea Aarrestad, Steffen Bähr, Jürgen Becker, Anne-Sophie Berthold, Richard J. Bonventre, Tomás E. Müller-Bravo, Markus Diefenthaler, Zhen Dong, Nick Fritzsche, Amir Gholami, Ekaterina Govorkova, Dongning Guo, Kyle J. Hazelwood, Christian Herwig, Babar Khan, Sehoon Kim, Thomas Klijnsma, Yaling Liu, Kin Ho Lo, Tri Nguyen, Gianantonio Pezzullo, Seyedramin Rasoulinezhad, Ryan A. Rivera, Kate Scholberg, Justin Selig, Sougata Sen, Dmitri Strukov, William Tang, Savannah Thais, Kai Lukas Unger, Ricardo Vilalta, Belinavon Krosigk, Shen Wang, Thomas K. Warburton
2022 A conf
Hessian-Aware Pruning and Optimal Neural Implant.
WACV
Shixing Yu, Zhewei Yao, Amir Gholami, Zhen Dong, Sehoon Kim, Michael W. Mahoney, Kurt Keutzer
2022 Misc conf
Integer-Only Zero-Shot Quantization for Efficient Speech Recognition.
ICASSP
Sehoon Kim, Amir Gholami, Zhewei Yao, Nicholas Lee, Patrick Wang, Aniruddha Nrusimha, Bohan Zhai, Tianren Gao, Michael W. Mahoney, Kurt Keutzer
2022 A* conf
Learned Token Pruning for Transformers.
KDD
Sehoon Kim, Sheng Shen, David Thorsley, Amir Gholami, Woosuk Kwon, Joseph Hassoun, Kurt Keutzer
2022 J jnl
Road accident risk prediction using generalized regression neural network optimized with self-organizing map.
Neural Comput. Appl.
Neda Kaffash-Charandabi, Amir Gholami, Ali Abdollahzadeh Bina
2022 A* conf
Squeezeformer: An Efficient Transformer for Automatic Speech Recognition.
NeurIPS
Sehoon Kim, Amir Gholami, Albert E. Shaw, Nicholas Lee, Karttikeya Mangalam, Jitendra Malik, Michael W. Mahoney, Kurt Keutzer
2022 J jnl
Squeezeformer: An Efficient Transformer for Automatic Speech Recognition.
CoRR
Sehoon Kim, Amir Gholami, Albert E. Shaw, Nicholas Lee, Karttikeya Mangalam, Jitendra Malik, Michael W. Mahoney, Kurt Keutzer
2021 J jnl
A Survey of Quantization Methods for Efficient Neural Network Inference.
CoRR
Amir Gholami, Sehoon Kim, Zhen Dong, Zhewei Yao, Michael W. Mahoney, Kurt Keutzer
2021 A* conf
ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning.
AAAI
Zhewei Yao, Amir Gholami, Sheng Shen, Mustafa Mustafa, Kurt Keutzer, Michael W. Mahoney
2021 J jnl
Applications and Techniques for Fast Machine Learning in Science.
CoRR
Allison McCarn Deiana, Nhan Tran, Joshua Agar, Michaela Blott, Giuseppe Di Guglielmo, Javier M. Duarte, Philip C. Harris, Scott Hauck, Mia Liu, Mark S. Neubauer, Jennifer Ngadiuba, Seda Ogrenci Memik, Maurizio Pierini, Thea Aarrestad, Steffen Bähr, Jürgen Becker, Anne-Sophie Berthold, Richard J. Bonventre, Tomás E. Müller-Bravo, Markus Diefenthaler, Zhen Dong, Nick Fritzsche, Amir Gholami, Ekaterina Govorkova, Kyle J. Hazelwood, Christian Herwig, Babar Khan, Sehoon Kim, Thomas Klijnsma, Yaling Liu, Kin Ho Lo, Tri Nguyen, Gianantonio Pezzullo, Seyedramin Rasoulinezhad, Ryan A. Rivera, Kate Scholberg, Justin Selig, Sougata Sen, Dmitri Strukov, William Tang, Savannah Thais, Kai Lukas Unger, Ricardo Vilalta, Belinavon Krosigk, Thomas K. Warburton, Maria Acosta Flechas, Anthony Aportela, Thomas Calvet, Leonardo Cristella, Daniel Diaz, Caterina Doglioni, Maria Domenica Galati, Elham E Khoda, Farah Fahim, Davide Giri, Benjamin Hawks, Duc Hoang, Burt Holzman, Shih-Chieh Hsu, Sergo Jindariani, Iris Johnson, Raghav Kansal, Ryan Kastner, Erik Katsavounidis, Jeffrey D. Krupa, Pan Li, Sandeep Madireddy, Ethan Marx, Patrick McCormack, Andres Meza, Jovan Mitrevski, Mohammed Attia Mohammed, Farouk Mokhtar, Eric A. Moreno, Srishti Nagu, Rohin Narayan, Noah Palladino, Zhiqiang Que, Sang Eon Park, Subramanian Ramamoorthy, Dylan S. Rankin, Simon Rothman, Ashish Sharma, Sioni Summers, Pietro Vischia, Jean-Roch Vlimant, Olivia Weng
2021 A* conf
Characterizing possible failure modes in physics-informed neural networks.
NeurIPS
Aditi S. Krishnapriyan, Amir Gholami, Shandian Zhe, Robert M. Kirby, Michael W. Mahoney
2021 J jnl
Characterizing possible failure modes in physics-informed neural networks.
CoRR
Aditi S. Krishnapriyan, Amir Gholami, Shandian Zhe, Robert M. Kirby, Michael W. Mahoney
2021 C conf
Denoising and Bad Data Detection in Distribution Phasor Measurements using Filtering, Clustering and Koopman Mode Analysis.
IAS
Amirkhosro Vosughi, Amir Gholami, Anurag K. Srivastava
2021 A* conf
HAWQ-V3: Dyadic Neural Network Quantization.
ICML
Zhewei Yao, Zhen Dong, Zhangcheng Zheng, Amir Gholami, Jiali Yu, Eric Tan, Leyuan Wang, Qijing Huang, Yida Wang, Michael W. Mahoney, Kurt Keutzer
2021 J jnl
Hessian-Aware Pruning and Optimal Neural Implant.
CoRR
Shixing Yu, Zhewei Yao, Amir Gholami, Zhen Dong, Michael W. Mahoney, Kurt Keutzer
2021 A* conf
I-BERT: Integer-only BERT Quantization.
ICML
Sehoon Kim, Amir Gholami, Zhewei Yao, Michael W. Mahoney, Kurt Keutzer
2021 J jnl
I-BERT: Integer-only BERT Quantization.
CoRR
Sehoon Kim, Amir Gholami, Zhewei Yao, Michael W. Mahoney, Kurt Keutzer
2021 J jnl
Learned Token Pruning for Transformers.
CoRR
Sehoon Kim, Sheng Shen, David Thorsley, Amir Gholami, Joseph Hassoun, Kurt Keutzer
2021 J jnl
Q-ASR: Integer-only Zero-shot Quantization for Efficient Speech Recognition.
CoRR
Sehoon Kim, Amir Gholami, Zhewei Yao, Aniruddha Nrusimha, Bohan Zhai, Tianren Gao, Michael W. Mahoney, Kurt Keutzer
2020 J jnl
ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning.
CoRR
Zhewei Yao, Amir Gholami, Sheng Shen, Kurt Keutzer, Michael W. Mahoney
2020 A* conf
Boundary thickness and robustness in learning models.
NeurIPS
Yaoqing Yang, Rajiv Khanna, Yaodong Yu, Amir Gholami, Kurt Keutzer, Joseph E. Gonzalez, Kannan Ramchandran, Michael W. Mahoney
2020 J jnl
Boundary thickness and robustness in learning models.
CoRR
Yaoqing Yang, Rajiv Khanna, Yaodong Yu, Amir Gholami, Kurt Keutzer, Joseph E. Gonzalez, Kannan Ramchandran, Michael W. Mahoney
2020 — conf
Checkmate: Breaking the Memory Wall with Optimal Tensor Rematerialization.
MLSys
Paras Jain, Ajay Jain, Aniruddha Nrusimha, Amir Gholami, Pieter Abbeel, Kurt Keutzer, Ion Stoica, Joseph Gonzalez
2020 A* conf
HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks.
NeurIPS
Zhen Dong, Zhewei Yao, Daiyaan Arfeen, Amir Gholami, Michael W. Mahoney, Kurt Keutzer
2020 J jnl
HAWQV3: Dyadic Neural Network Quantization.
CoRR
Zhewei Yao, Zhen Dong, Zhangcheng Zheng, Amir Gholami, Jiali Yu, Eric Tan, Leyuan Wang, Qijing Huang, Yida Wang, Michael W. Mahoney, Kurt Keutzer
2020 A* conf
Inefficiency of K-FAC for Large Batch Size Training.
AAAI
Linjian Ma, Gabe Montague, Jiayu Ye, Zhewei Yao, Amir Gholami, Kurt Keutzer, Michael W. Mahoney
2020 A* conf
PowerNorm: Rethinking Batch Normalization in Transformers.
ICML
Sheng Shen, Zhewei Yao, Amir Gholami, Michael W. Mahoney, Kurt Keutzer
2020 — conf
PyHessian: Neural Networks Through the Lens of the Hessian.
IEEE BigData
Zhewei Yao, Amir Gholami, Kurt Keutzer, Michael W. Mahoney
2020 A* conf
Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT.
AAAI
Sheng Shen, Zhen Dong, Jiayu Ye, Linjian Ma, Zhewei Yao, Amir Gholami, Michael W. Mahoney, Kurt Keutzer
2020 J jnl
Rethinking Batch Normalization in Transformers.
CoRR
Sheng Shen, Zhewei Yao, Amir Gholami, Michael W. Mahoney, Kurt Keutzer
2020 A* conf
ZeroQ: A Novel Zero Shot Quantization Framework.
CVPR
Yaohui Cai, Zhewei Yao, Zhen Dong, Amir Gholami, Michael W. Mahoney, Kurt Keutzer
2020 J jnl
ZeroQ: A Novel Zero Shot Quantization Framework.
CoRR
Yaohui Cai, Zhewei Yao, Zhen Dong, Amir Gholami, Michael W. Mahoney, Kurt Keutzer
2019 C conf
A Simulation Platform Design and Kinematics Analysis of MRL-HSL Humanoid Robot.
RoboCup
Amir Gholami, Milad Moradi, Majid Majidi
2019 J jnl
A novel LMI-based robust model predictive control for DFIG-based wind energy conversion systems.
Kybernetika
Amir Gholami, Alireza Sahab, Abdolreza Tavakoli, Behnam Alizadeh
2019 J jnl
ANODE: Unconditionally Accurate Memory-Efficient Gradients for Neural ODEs.
CoRR
Amir Gholami, Kurt Keutzer, George Biros
2019 J jnl
ANODEV2: A Coupled Neural ODE Evolution Framework.
CoRR
Tianjun Zhang, Zhewei Yao, Amir Gholami, Kurt Keutzer, Joseph Gonzalez, George Biros, Michael W. Mahoney
2019 A* conf
ANODEV2: A Coupled Neural ODE Framework.
NeurIPS
Tianjun Zhang, Zhewei Yao, Amir Gholami, Joseph E. Gonzalez, Kurt Keutzer, Michael W. Mahoney, George Biros
2019 J jnl
CLAIRE: A Distributed-Memory Solver for Constrained Large Deformation Diffeomorphic Image Registration.
SIAM J. Sci. Comput.
Andreas Mang, Amir Gholami, Christos Davatzikos, George Biros
2019 J jnl
Checkmate: Breaking the Memory Wall with Optimal Tensor Rematerialization.
CoRR
Paras Jain, Ajay Jain, Aniruddha Nrusimha, Amir Gholami, Pieter Abbeel, Kurt Keutzer, Ion Stoica, Joseph E. Gonzalez
2019 J jnl
Co-design of deep neural nets and neural net accelerators for embedded vision applications.
IBM J. Res. Dev.
Alon Amid, Kiseok Kwon, Amir Gholami, Bichen Wu, Krste Asanovic, Kurt Keutzer
2019 J jnl
HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks.
CoRR
Zhen Dong, Zhewei Yao, Yaohui Cai, Daiyaan Arfeen, Amir Gholami, Michael W. Mahoney, Kurt Keutzer
2019 A* conf
HAWQ: Hessian AWare Quantization of Neural Networks With Mixed-Precision.
ICCV
Zhen Dong, Zhewei Yao, Amir Gholami, Michael W. Mahoney, Kurt Keutzer
2019 J jnl
HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision.
CoRR
Zhen Dong, Zhewei Yao, Amir Gholami, Michael W. Mahoney, Kurt Keutzer
2019 J jnl
Inefficiency of K-FAC for Large Batch Size Training.
CoRR
Linjian Ma, Gabe Montague, Jiayu Ye, Zhewei Yao, Amir Gholami, Kurt Keutzer, Michael W. Mahoney
2019 C conf
MRL Champion Team Paper in Humanoid TeenSize League of RoboCup 2019.
RoboCup
Hamed Mahmudi, Amir Gholami, Mohammad Hossein Delavaran, Soheil Khatibi, Saeid Bazargan, Milad Moradi, Bita Alaee, Arash Rahmani, Kazem Firouzmandi Bandpey, Peyman Fallahzadeh, Meisam Teimouri
2019 J jnl
PyHessian: Neural Networks Through the Lens of the Hessian.
CoRR
Zhewei Yao, Amir Gholami, Kurt Keutzer, Michael W. Mahoney
2019 J jnl
Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT.
CoRR
Sheng Shen, Zhen Dong, Jiayu Ye, Linjian Ma, Zhewei Yao, Amir Gholami, Michael W. Mahoney, Kurt Keutzer
2019 A* conf
Trust Region Based Adversarial Attack on Neural Networks.
CVPR
Zhewei Yao, Amir Gholami, Peng Xu, Kurt Keutzer, Michael W. Mahoney
2018 — conf
A Novel Domain Adaptation Framework for Medical Image Segmentation.
BrainLes@MICCAI (2)
Amir Gholami, Shashank Subramanian, Varun Shenoy, Naveen Himthani, Xiangyu Yue, Sicheng Zhao, Peter H. Jin, George Biros, Kurt Keutzer
2018 J jnl
A Novel Domain Adaptation Framework for Medical Image Segmentation.
CoRR
Amir Gholami, Shashank Subramanian, Varun Shenoy, Naveen Himthani, Xiangyu Yue, Sicheng Zhao, Peter H. Jin, George Biros, Kurt Keutzer
2018 J jnl
CLAIRE: A distributed-memory solver for constrained large deformation diffeomorphic image registration.
CoRR
Andreas Mang, Amir Gholami, Christos Davatzikos, George Biros
2018 J jnl
Co-Design of Deep Neural Nets and Neural Net Accelerators for Embedded Vision Applications.
CoRR
Kiseok Kwon, Alon Amid, Amir Gholami, Bichen Wu, Krste Asanovic, Kurt Keutzer
2018 A* conf
Co-design of deep neural nets and neural net accelerators for embedded vision applications.
DAC
Kiseok Kwon, Alon Amid, Amir Gholami, Bichen Wu, Krste Asanovic, Kurt Keutzer
2018 A* conf
Hessian-based Analysis of Large Batch Training and Robustness to Adversaries.
NeurIPS
Zhewei Yao, Amir Gholami, Qi Lei, Kurt Keutzer, Michael W. Mahoney
2018 J jnl
Hessian-based Analysis of Large Batch Training and Robustness to Adversaries.
CoRR
Zhewei Yao, Amir Gholami, Qi Lei, Kurt Keutzer, Michael W. Mahoney
2018 B conf
Integrated Model, Batch, and Domain Parallelism in Training Neural Networks.
SPAA
Amir Gholami, Ariful Azad, Peter H. Jin, Kurt Keutzer, Aydin Buluç
2018 J jnl
Large batch size training of neural networks with adversarial training and second-order information.
CoRR
Zhewei Yao, Amir Gholami, Kurt Keutzer, Michael W. Mahoney
2018 J jnl
On the Computational Inefficiency of Large Batch Sizes for Stochastic Gradient Descent.
CoRR
Noah Golmant, Nikita Vemuri, Zhewei Yao, Vladimir Feinberg, Amir Gholami, Kai Rothauge, Michael W. Mahoney, Joseph Gonzalez
2018 J jnl
PDE-constrained optimization in medical image analysis.
CoRR
Andreas Mang, Amir Gholami, Christos Davatzikos, George Biros
2018 J jnl
Parameter Re-Initialization through Cyclical Batch Size Schedules.
CoRR
Norman Mu, Zhewei Yao, Amir Gholami, Kurt Keutzer, Michael W. Mahoney
2018 — conf
SqueezeNext: Hardware-Aware Neural Network Design.
CVPR Workshops
Amir Gholami, Kiseok Kwon, Bichen Wu, Zizheng Tai, Xiangyu Yue, Peter H. Jin, Sicheng Zhao, Kurt Keutzer
2018 J jnl
SqueezeNext: Hardware-Aware Neural Network Design.
CoRR
Amir Gholami, Kiseok Kwon, Bichen Wu, Zizheng Tai, Xiangyu Yue, Peter H. Jin, Sicheng Zhao, Kurt Keutzer
2018 J jnl
Trust Region Based Adversarial Attack on Neural Networks.
CoRR
Zhewei Yao, Amir Gholami, Peng Xu, Kurt Keutzer, Michael W. Mahoney
2017 A conf
A framework for scalable biophysics-based image analysis.
SC
Amir Gholami, Andreas Mang, Klaudius Scheufele, Christos Davatzikos, Miriam Mehl, George Biros
2017 J jnl
Integrated Model and Data Parallelism in Training Neural Networks.
CoRR
Amir Gholami, Ariful Azad, Kurt Keutzer, Aydin Buluç
2016 A conf
Distributed-memory large deformation diffeomorphic 3D image registration.
SC
Andreas Mang, Amir Gholami, George Biros
2016 J jnl
Distributed-memory large deformation diffeomorphic 3D image registration.
CoRR
Andreas Mang, Amir Gholami, George Biros
2016 J jnl
FFT, FMM, or Multigrid? A comparative Study of State-Of-the-Art Poisson Solvers for Uniform and Nonuniform Grids in the Unit Cube.
SIAM J. Sci. Comput.
Amir Gholami, Dhairya Malhotra, Hari Sundar, George Biros
2015 J jnl
AccFFT: A library for distributed-memory FFT on CPU and GPU architectures.
CoRR
Amir Gholami, Judith Hill, Dhairya Malhotra, George Biros
2014 A conf
A Volume Integral Equation Stokes Solver for Problems with Variable Coefficients.
SC
Dhairya Malhotra, Amir Gholami, George Biros
2014 J jnl
FFT, FMM, or MULTIGRID? A comparative study of state-of-the-art poisson solvers.
CoRR
Amir Gholami, Dhairya Malhotra, Hari Sundar, George Biros