253 citations · 451 across the 17 of their papers we have counts for
17 papers
Uncertainty-aware Self-supervised Learning for Cross-domain Technical Skill Assessment in Robot-assisted Surgery
Ziheng Wang, Andrea Mariani, Arianna Menciassi +2
Objective technical skill assessment is crucial for effective training of new surgeons in robot-assisted surgery. With advancements in surgical training programs in both physical a…
Effective Random Test Generation for Deep Learning Compilers
Luyao Ren, ZiHeng Wang, Yingfei Xiong +3
Deep learning compilers help address the difficulties of deploying deep learning models on diverse types of hardware. Testing deep learning compilers is highly crucial, because the…
Continuous-time stochastic gradient descent for optimizing over the stationary distribution of stochastic differential equations
Ziheng Wang, Justin Sirignano
We develop a new continuous-time stochastic gradient descent method for optimizing over the stationary distribution of stochastic differential equation (SDE) models. The algorithm…
Global Convergence of the ODE Limit for Online Actor-Critic Algorithms in Reinforcement Learning
Ziheng Wang, Justin Sirignano
Actor-critic algorithms are widely used in reinforcement learning, but are challenging to mathematically analyse due to the online arrival of non-i.i.d. data samples. The distribut…
Compiling Halide Programs to Push-Memory Accelerators
Qiaoyi Liu, Dillon Huff, Jeff Setter +8
Image processing and machine learning applications benefit tremendously from hardware acceleration, but existing compilers target either FPGAs, which sacrifice power and performanc…
Investigating the integrate and fire model as the limit of a random discharge model: a stochastic analysis perspective
Jian-Guo Liu, Ziheng Wang, Yantong Xie +2
In the mean field integrate-and-fire model, the dynamics of a typical neuron within a large network is modeled as a diffusion-jump stochastic process whose jump takes place once th…
SparseDNN: Fast Sparse Deep Learning Inference on CPUs
Ziheng Wang
The last few years have seen gigantic leaps in algorithms and systems to support efficient deep learning inference. Pruning and quantization algorithms can now consistently compres…
Investigating the integrate and fire model as the limit of a random discharge model: a stochastic analysis perspective
Jian-Guo Liu, Ziheng Wang, Yantong Xie +2
In the mean field integrate-and-fire model, the dynamics of a typical neuron within a large network is modeled as a diffusion-jump stochastic process whose jump takes place once th…
SparseRT: Accelerating Unstructured Sparsity on GPUs for Deep Learning Inference
Ziheng Wang
In recent years, there has been a flurry of research in deep neural network pruning and compression. Early approaches prune weights individually. However, it is difficult to take a…
Rigorous justification of the Fokker-Planck equations of neural networks based on an iteration perspective
Jian-guo Liu, Ziheng Wang, Yuan Zhang +1
In this work, the primary goal is to establish rigorous connection between the Fokker-Planck equation of neural networks with its microscopic model: the diffusion-jump stochastic p…
Structured Pruning of Large Language Models
Ziheng Wang, Jeremy Wohlwend, Tao Lei
Large language models have recently achieved state of the art performance across a wide variety of natural language tasks. Meanwhile, the size of these models and their latency hav…
Accelerated CNN Training Through Gradient Approximation
Ziheng Wang, Sree Harsha Nelaturu
Training deep convolutional neural networks such as VGG and ResNet by gradient descent is an expensive exercise requiring specialized hardware such as GPUs. Recent works have exami…
Transferrable Operative Difficulty Assessment in Robot-assisted Teleoperation: A Domain Adaptation Approach
Ziheng Wang, Cong Feng, Jie Zhang +1
Providing an accurate and efficient assessment of operative difficulty is important for designing robot-assisted teleoperation interfaces that are easy and natural for human operat…
SATR-DL: Improving Surgical Skill Assessment and Task Recognition in Robot-assisted Surgery with Deep Neural Networks
Ziheng Wang, Ann Majewicz Fey
Purpose: This paper focuses on an automated analysis of surgical motion profiles for objective skill assessment and task recognition in robot-assisted surgery. Existing techniques…
Deep Learning with Convolutional Neural Network for Objective Skill Evaluation in Robot-assisted Surgery
Ziheng Wang, Ann Majewicz Fey
With the advent of robot-assisted surgery, the role of data-driven approaches to integrate statistics and machine learning is growing rapidly with prominent interests in objective…
A Generative Restricted Boltzmann Machine Based Method for High-Dimensional Motion Data Modeling
Siqi Nie, Ziheng Wang, Qiang Ji
Many computer vision applications involve modeling complex spatio-temporal patterns in high-dimensional motion data. Recently, restricted Boltzmann machines (RBMs) have been widely…
A Hierarchical Probabilistic Model for Facial Feature Detection
Yue Wu, Ziheng Wang, Qiang Ji
Facial feature detection from facial images has attracted great attention in the field of computer vision. It is a nontrivial task since the appearance and shape of the face tend t…