Search Results for author:
Found 8 papers, 1 papers with code
ADA-GP: Accelerating DNN Training By Adaptive Gradient Prediction
Neural network training is inherently sequential where the layers finish the forward propagation in succession, followed by the calculation and back-propagation of gradients (based on a loss function) starting from the last layer.
Large Language Models Based Automatic Synthesis of Software Specifications
As software systems grow in complexity and scale, the number of configurations and associated specifications required to ensure the correct operation can become large and prohibitively difficult to manipulate manually.
Synthesizing Programs with Continuous Optimization
In this paper, we present a novel formulation of program synthesis as a continuous optimization problem and use a state-of-the-art evolutionary approach, known as Covariance Matrix Adaptation Evolution Strategy to solve the problem.
MERCURY: Accelerating DNN Training By Exploiting Input Similarity
If the Signature of a new input vector matches that of an already existing vector in the MCACHE, the two vectors are found to have similarities.
Continual Learning Approach for Improving the Data and Computation Mapping in Near-Memory Processing System
Along with NMP and memory system development, the mapping for placing data and guiding computation in the memory-cube network has become crucial in driving the performance improvement in NMP.
The Case for Learning Application Behavior to Improve Hardware Energy Efficiency
During the execution of an unseen application, the model uses the learned knowledge to reconfigure hardware resources in order to maximize energy efficiency.
Learning Fitness Functions for Machine Programming
The problem of automatic software generation is known as Machine Programming.
A Zero-Positive Learning Approach for Diagnosing Software Performance Regressions
This is, in part, due to the emergence of a wide range of novel techniques in machine learning.
