Amir Gholami

About

Amir Gholami is a postdoctoral research fellow in BAIR Lab. He received his PhD from UT Austin, working on large scale 3D image segmentation, a research topic which received UT Austin’s best doctoral dissertation award in 2018. He is a Melosh Medal finalist, the recipient of best student paper award in SC'17, Gold Medal in the ACM Student Research Competition, as well as best student paper finalist in SC’14. His current research includes different aspects of Systems for Machine Learning (SysML), and large scale training of Neural Networks (resume).

Contact Email: "amirgh _at_ berkeley . edu".

Recent News

[02/25/20]: I will give the opening Keynote talk for NSF Workshop on Smart Cyberinfrastructure.

[02/10/20]: I will give an invited lecture in UC Berkeley's EE 290 course on Efficient Neural Network Training and Inference.

[02/06/20]: I will give an invited lecture in Stanford's CS 217 course on Precision and Quantized Training for Deep Learning.

[11/11/19]: Two papers accepted in AAAI'20: Q-BERT, and Inefficiency of K-FAC for large batch size training.

[09/30/19]: Two papers accepted in NeurIPS'19: ANODEV2 in the main conference, and our work on Trace Weighted Quantization as spotlight in beyond first order methods workshop.

[09/29/19]: I will be presenting our work on second-order quantization (HAWQ and Q-BERT) in BLISS seminar on October 2nd.

[08/15/19]: Very excited to participate in AI4ALL, an annual teaching program for high school students from underrepresented communities to promote diversity and inclusion in AI.

[05/07/19]: Congratulations to Linjian Ma (now PhD student at UIUC), Jiayu Ye (now at Google), and Gabe Montague (co-founder of Bike and Pedal) on successfully defending their Masters project.

[03/21/19]: Will be giving a talk at BSTARS'19. Many thanks to the Berkeley Statistics department for the invitation.

[03/01/19]: Our Trust Region paper has been accepted to CVPR'19!

[02/28/19]: Will be giving a talk in Fifth Annual Industry Day at Simons Institute

[11/06/18]: Three papers accepted in NeurIPS'18 (one main conference and two workshops)

[11/01/18]: I will be giving a talk in Stanford CME-510 lecture series

[03/30/18]: Just learned that my PhD thesis has won UT Austin's 2018 Outstanding Disseration Award. Thanks George for your great mentorship

[03/28/18]: We have released SqueezeNext, the smallest neural network desgined so far (112x smaller than AlexNet)

[03/05/18]: Bichen's paper is selected for spotlight in CVPR'18

[02/26/18]: Selected as a finalist for Robert J. Melosh Medal. Very excited to visit Duke University

[02/08/18]: Will be giving a lecture in CS267 on GPUs [Watch Here]

[11/21/17]: Our paper won the Best Student Paper award at SC'17!

Publications

Papers

Rethinking Batch Normalization in Transformers
S. Shen, Z. Yao, A. Gholami, M. Mahoney, K. Keutzer
(arxiv:2003.07845), 2020.

ZeroQ: A Novel Zero Shot Quantization Framework,
Y. Cai, Z. Yao, Z. Dong, A. Gholami, M. Mahoney, K. Keutzer
Accepted in CVPR'20 (arxiv:2001.00281), 2020. [Code]

PyHessian: Neural Networks Through the Lens of the Hessian,
Z. Yao, A. Gholami, K. Keutzer, M. Mahoney
(arxiv:1912.07145), 2019. [Code]

HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks,
Z. Dong, Z. Yao, Y. Cai, D. Arfeen, A. Gholami, M. Mahoney, K. Keutzer
(arxiv:1911.03852), 2019.

Checkmate: Breaking the Memory Wall with Optimal Tensor Rematerialization,
P. Jain, A. Jain, A. Nrusimha , A. Gholami, P. Abbeel, K. Keutzer, I. Stoica, J. Gonzalez
Accepted in MLSys'20 (arxiv:1910.02653). [Code]

Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT,
S. Shen, Z. Dong, J. Ye, L. Ma, Z. Yao, A. Gholami, M. Mahoney, K. Keutzer,
AAAI'20 (arxiv:1909.05840), 2020.

ANODEV2: A Coupled Neural ODE Evolution Framework,
T. Zhang, Z. Yao, A. Gholami, K Keutzer, J. Gonzalez, G. Biros, MW. Mahoney,
NeurIPS'19 (Accepted), arxiv:1905.03696, 2019.

HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision,
Z Dong, Z Yao, A Gholami, K Keutzer, MW Mahoney,
Accepted in ICCV'19 (arxiv:1905.03696), 2019.

Inefficiency of K-FAC for Large Batch Size Training,
L. Ma, G. Montague, J. Ye, Z. Yao, A. Gholami, K. Keutzer, MW. Mahoney,
AAAI'20 (arxiv:1903.06237), 2020.

ANODE: Unconditionally AccurateMemory-Efficient Gradients for Neural ODEs,
A. Gholami, K. Keutzer, G. Biros,
International Joint Conferences on Artificial Intelligence (IJCAI'19), 2019.

Trust region based adversarial attack on neural networks,
Z. Yao, A. Gholami, P. Xu, K. Keutzer, and M. Mahoney,
CVPR'19, 2019.

A Novel Domain Adaptation Framework for Medical Image Segmentation,
A. Gholami, S. Subramanian, V. Shenoy, N. Himthani, X. Yue, S. Zhao, P. Jin, G. Biros, K. Keutzer,
Lecture Notes in Computer Science (LNCS), Springer, 2018.

Simulation of glioblastoma growth using a 3D multispecies tumor model with mass effect,
S. Subramanian, A. Gholami, G. Biros,
Journal of Mathematical Biology (JMatBio), 2019.

Large Batch Size Training of Neural Networks with Adversarial Training and Second-Order Information,
Z. Yao, A. Gholami, K. Keutzer, M. Mahoney,
arxiv preprint, arxiv:1810.01021, 2018.

On the Computational Inefficiency of Large Batch Sizes for Stochastic Gradient Descent,
N. Golmant, N. Vemuri, Z. Yao, V. Feinberg, A. Gholami, K. Rothauge, M. Mahoney, J. Gonzalez,
arxiv preprint, arxiv:1811.12941, 2018.

Co-Design of Deep Neural Nets and Neural Net Accelerators for Embedded Vision Applications,
K. Kwon, A. Amid, A. Gholami, B. Wu, K. Keutzer,
Design Automation Conference (DAC'18), 2018.

Hessian-based Analysis of Large Batch Training and Robustness to Adversaries,
Z. Yao, A. Gholami, Q. Lei, K. Keutzer, M. Mahoney,
NeurIPS'18, 2018.

Integrated Model, Batch and Domain Parallelism in Training Neural Networks,
A. Gholami, A. Azad, P. Jin, K. Keutzer, A. Buluc,
ACM Symposium on Parallelism in Algorithms and Architectures(SPAA’18), 2018.

Shift: A zero flop, zero parameter alternative to spatial convolutions,
B. Wu, A. Wan, X. Yue, P. Jin, S. Zhao, N. Golmant, A. Gholami, J. Gonzalez, K. Keutzer,
CVPR'18 (Spotlight talk), 2018.

Personalized Emotion Recognition by Personality-aware High-order Learning of Physiological Signals,
S. Zhao, A. Gholami, G. Ding, J. Han, K. Keutzer,
ACM Transactions on MultiMedia Computing, 2018.

CLAIRE: A distributed-memory solver for constrained large deformation diffeomorphic image registration,
A. Mang, A. Gholami, C. Davatzikos, G. Biros,
arxiv preprint, arxiv:1808.04487, 2018.

Coupling brain-tumor biophysical models and diffeomorphic image registration,
K. Scheufele, A. Mang, A. Gholami, C. Davatzikos, G. Biros, and M. Mehl,
Computer Methods in Applied Mechanics and Engineering, 2019.

SIBIA-GlS: Scalable biophysics-based image analysis for glioma segmentation,
A. Mang, S. Tharakan A. Gholami, N. Himthani, S. Subramanian, J. Levitt, M. Azmat, K. Scheufele, M. Mehl, C. Davatzikos, B. Barth, and G. Biros,
The multimodal brain tumor image segmentation benchmark (BRATS), MICCAI, 2017.

A framework for scalable biophysics-based image analysis,
A. Gholami, A. Mang, K. Scheufele, C. Davatzikos, M. Mehl, and G. Biros,
Proceedings of ACM/IEEE SuperComputing Conference (SC'17), 2017.

PDE constrained optimization in medical image analysis,
A. Mang, A. Gholami, C. Davatzikos, and G. Biros,
Optimization and Engineering (accepted), 2017.

Distributed-memory large-deformation diffeomorphic 3D image registration,
A. Mang, A. Gholami, and G. Biros,
Proceedings of ACM/IEEE SuperComputing Conference (SC16), 2016.

AccFFT: A library for distributed-memory FFT on CPU and GPU architectures,
A. Gholami, J. Hill, D. Malhotra, and G. Biros,
arxiv preprint, arxiv:1506.07933, 2018.

A volume integral equation Stokes solver for problems with variable coefficients,
D. Malhotra, A. Gholami, and G. Biros,
Proceedings of ACM/IEEE SuperComputing Conference (SC14), 2014 (Best Student Paper Finalist).

An inverse problem formulation for parameter estimation of a reaction–diffusion model of low grade gliomas,
A. Gholami, A. Mang, and G. Biros,
Journal of mathematical biology, Vol. 72, pp 409-433, 2015.

FFT, FMM, or Multigrid? A comparative Study of State-Of-the-Art Poisson Solvers for Uniform and Nonuniform Grids in the Unit Cube,
A. Gholami, D. Malhotra, H. Sundar and G. Biros. ,
SIAM Journal on Scientific Computing, Vol. 38 (3), 2016.

Workshops

Trace weighted Hessian-aware quantization,
Z. Dong, Z. Yao, D. Arfeen, Y. Cai, A. Gholami, M. Mahoney, and K. Keutzer,
Spotlight at NuerIPS'19 workshop on Beyond First-Order Optimization Methods in Machine Learning, 2019.

Parameter re-initialization through cyclical batch- scheduling,
N. Mu, Z. Yao, A. Gholami, K. Keutzer, and M. Mahoney,
SysML Workshop at NuerIPS'18 (arxiv:1812.01216), 2018.

SqueezeNext: Hardware-Aware Neural Network Design,
A. Gholami, K. Kwon, B. Wu, Z. Tai, X. Yue, P. Jin, S. Zhao, K. Keutzer,
ECV Workshop at CVPR'18, 2018.

Communication analysis of hybrid model and data parallelism in training neural networks,
Amir Gholami, Ariful Azad, Kurt Keutzer, and Aydin Buluc,
Deep Learning at Supercomputer Scale, NeurIPS'17, 2017.

Selected Talks

UC Berkeley, RiseLab Retreat, Jan. 2020,
HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks.

UC Berkeley, BLISS Seminar, Oct. 2019,
Systematic Quantization of Neural Networks Through Second-Order Information.

Facebook, AI Systems Faculty Summit, Sep. 2019,
Efficient Neural Networks through Systematic Quantization.

BSTARS'19, Berkeley Statistics Department, Mar. 2019,
Neural Networks Through the Lens of the Hessian.

Berkeley Simons Institute, 5th Annual Industry Day, Feb. 2019,
ANODE: Unconditionally Accurate Memory-Efficient Gradients for Neural ODEs.

Simons Randomized Numerical Linear Algebra and Applications Workshop, Sep. 2018,
Large Scale Stochastic Training of Neural Networks.

Simons Data Science Finale Workshop, Dec. 2018,
Towards Robust Second-order Training of Neural Networks.

Simons Weekly Optimization Reading Group, Oct. 2018,
Second order optimization for convex and non-convex problems.

NERSC Data Seminar, Dec. 2018,
Beyond SGD: Robust Optimization and Second-Order Information for Large-Scale Training of Neural Networks .

Stanford, CME 510: Linear Algebra and Optimization Seminar, Nov. 2018,
Large-scale training of Neural Networks .

UCSF Radiology Department, Oct. 2018 ,
A Domain Adaptation framework for Neural Network Based Medical Image Segmentation.

Intel AI Meeting, Oct. 2018,
Autonomous Driving Challenges in Computer Vision Research.

Facebook AI Research, Sep. 2018,
Challenges for Distributed Training of Neural Networks.

Microsoft Research, Aug. 2018,
Large Scale Training of Neural Networks .

Berkeley Scientific Computing and Matrix Computations Seminar, Sep. 2017,
A Framework for Scalable Biophysics-based Image Analysis .

Stanford, ICME Star Talk Series, 2017,
Fast algorithms for inverse problems with parabolic pde constraints with application to biophysics-based image analysis,

SIAM Minisymposium on Imaging Sciences, Albuquerque, NM, USA, 2016,
On preconditioning Newton method for PDE constrained optimization problems.

13th U.S. National Congress on Computational Mechanics, San Diego, CA, USA, 2015,
Challenges for exascale scalability of elliptic solvers using a model Poisson solver and comparing state-of-the art methods.

SIAM CSE Minisymposium, Salt Lake, Utah, USA, 2015,
Parameter estimation for malignant brain tumors.

12th U.S. National Congress on Computational Mechanics, Raleigh, NC, USA, 2013,
A numerical algorithm for biophysically-constrained parameter estimation for tumor modeling and data assimilation with medical images.

SIAM Annual Meeting, San Diego, CA, USA, 2013,
Image-driven inverse problem for estimating initial distribution of brain tumor modeled by advection-diffusion-reaction equation.

Patents

Dynamic directional rounding,
A. Fit-Florea, A. Gholami, B. Ginsburg, and P. Davoodi.
Approved by Nvidia Patent Office (US patent pending), 2018.

Tensor processing using low precision format,
B. Ginsburg, S. Nikolaev, A. Kiswani, H. Wu, A. Gholami, S. Kierat, M. Houston, and A. Fit-Flores.
United States patent application US 15/624,577. 2017 Dec 28.

A novel high performance inplace transpose algorithm,
A. Gholami and B. Natarajan,
US Patent Pending, 2017.

Pool boiling cooling system.,
A. Gholami, R. Hosseini, M. Nabil, and M. H. Samadinia.
Iran Industrial Property Office, 68033, 2010.