Search Results for author:
Found 8 papers, 1 papers with code
An Evaluation of Real-time Adaptive Sampling Change Point Detection Algorithm using KCUSUM
Detecting abrupt changes in real-time data streams from scientific simulations presents a challenging task, demanding the deployment of accurate and efficient algorithms.
Learning Independent Program and Architecture Representations for Generalizable Performance Modeling
This paper proposes PerfVec, a novel deep learning-based performance modeling framework that learns high-dimensional, independent/orthogonal program and microarchitecture representations.
Stochastic Projective Splitting: Solving Saddle-Point Problems with Multiple Regularizers
We present a new, stochastic variant of the projective splitting (PS) family of algorithms for monotone inclusion problems.
SimNet: Accurate and High-Performance Computer Architecture Simulation using Deep Learning
While discrete-event simulators are essential tools for architecture research, design, and development, their practicality is limited by an extremely long time-to-solution for realistic applications under investigation.
BIG-bench Machine Learning
Vocal Bursts Intensity Prediction
Bounding the expected run-time of nonconvex optimization with early stopping
This work examines the convergence of stochastic gradient-based optimization algorithms that use early stopping based on a validation function.
On the expected running time of nonconvex optimization with early stopping
This work examines the convergence of stochastic gradient algorithms that use early stopping based on a validation function, wherein optimization ends when the magnitude of a validation function gradient drops below a threshold.
Layered SGD: A Decentralized and Synchronous SGD Algorithm for Scalable Deep Neural Network Training
The efficiency of the algorithm is tested by training a deep network on the ImageNet classification task.
The duality structure gradient descent algorithm: analysis and applications to neural networks
The decision of what layer to update is done in a greedy fashion, based on a rigorous lower bound on the improvement of the objective function for each choice of layer.
