Efficient

Efficient Numerical Methods for Scalable Bayesian Inference

-

B9 R2325

This talk will introduce and discuss the computational building blocks of Integrated Nested Laplace Approximations (INLA) and how these are implemented in software libraries such as R-INLA or DALIA.

Accelerating Branch-and-Bound Graph Algorithms with GPUs

-

B9 L2 R2325

This talk presents multiple techniques that we have developed to load balance the search tree traversal on GPUs and mitigate the strain on memory capacity and bandwidth.

From Dialects to Peptides: Scalable and Efficient AI for People

-

B9 L2 R2325

This talk presents a unified AI framework for decoding complex human and biological signals - spanning African and Arabic dialects to proteomics - by prioritizing rigorous measurement, cultural competence, and computational efficiency to ensure global scalability and accessibility.

Efficient and Accurate Numerical Methods for Transient Electromagnetic Analysis - 2020

-

KAUST

Electromagnetic devices and systems are at the heart of technological advances revolutionizing many fields of science and engineering including energy management, biomedical electronics, communications and computing, and even environmental monitoring and civil design. Many of these systems are electrically large, their frequency of operation has a wide dynamic range, their device components are geometrically intricate with dimensions varying by orders of magnitude, and finally their optimal design requires many repetitions of characterizations with different parameters.

Efficient Machine Learning across Hardware, Software, and Algorithms

-

B2 L5 R5209

Deep neural networks (DNNs) are revolutionizing computing, necessitating an integrated approach across the computing stack to optimize efficiency. In this talk, I will explore the frontier of DNN optimization, spanning algorithms, software, and hardware. We'll start with hardware-aware neural architecture search, demonstrating how tailoring DNN architectures to specific hardware can drastically enhance performance.