Related papers: Dynamic Aperture Optimization for the DAFNE Upgrad…
We propose a stochastic optimization method for minimizing loss functions, expressed as an expected value, that adaptively controls the batch size used in the computation of gradient approximations and the step size used to move along such…
We propose a continuous-time scheme for large-scale optimization that introduces individual, adaptive momentum coefficients regulated by the kinetic energy of each model parameter. This approach automatically adjusts to local landscape…
As an ever-increasing demand for high dynamic range (HDR) scene shooting, multi-exposure image fusion (MEF) technology has abounded. In recent years, multi-scale exposure fusion approaches based on detail-enhancement have led the way for…
High quality AI solutions require joint optimization of AI algorithms, such as deep neural networks (DNNs), and their hardware accelerators. To improve the overall solution quality as well as to boost the design productivity, efficient…
We present an adaptive extension of probe based global illumination solution that enhances the response to dynamic changes in the scene while while also enabling an order of magnitude increase in probe count. Our adaptive sampling strategy…
This paper presents a framework for dynamic object catching using a quadruped robot's front legs while it stands on its rear legs. The system integrates computer vision, trajectory prediction, and leg control to enable the quadruped to…
This work presents a highly optimized computational framework for the Discrete Dipole Approximation, a numerical method for calculating the optical properties associated with a target of arbitrary geometry that is widely used in…
The upgrade of the Swiss Light Source, called SLS 2.0, is scheduled for 2023-24. The current storage ring will be replaced by one based on multi-bend achromats, allowing for about 30 times higher brightness. Due to the stronger focusing and…
Feature based visual odometry and SLAM methods require accurate and fast correspondence matching between consecutive image frames for precise camera pose estimation in real-time. Current feature matching pipelines either rely solely on the…
The Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Lab is investigating a significant energy upgrade utilizing Fixed-Field Alternating-gradient (FFA) recirculating arcs. This upgrade requires the design of complex…
Fixed-point optimization of deep neural networks plays an important role in hardware based design and low-power implementations. Many deep neural networks show fairly good performance even with 2- or 3-bit precision when quantized weights…
This paper presents a novel numerical optimisation method for infinite dimensional optimisation. The functional optimisation makes minimal assumptions about the functional and without any specific knowledge on the derivative of the…
We present a novel dynamic configuration technique for deep neural networks that permits step-wise energy-accuracy trade-offs during runtime. Our configuration technique adjusts the number of channels in the network dynamically depending on…
A significant challenge in object detection is accurate identification of an object's position in image space, whereas one algorithm with one set of parameters is usually not enough, and the fusion of multiple algorithms and/or parameters…
We present a modified nudged elastic band routine that can reduce the number of force calls by more than 50% for bands with non-uniform convergence. The method, which we call "dyNEB", dynamically and selectively optimizes states based on…
In this paper, a self-adaptive contractive (SAC) algorithm is proposed for enhanced dynamic phasor estimation in the diverse operating conditions of modern power systems. At a high-level, the method is composed of three stages: parameter…
We propose a single-loop variance-reduced acceleration framework, which relates checkpoint update probabilities to momentum parameters, for solving the composite general convex problem where the smooth part has the finite-sum structure.…
Multimodal object detection leverages diverse modal information to enhance the accuracy and robustness of detectors. By learning long-term dependencies, Transformer can effectively integrate multimodal features in the feature extraction…
Recent focus on robustness to adversarial attacks for deep neural networks produced a large variety of algorithms for training robust models. Most of the effective algorithms involve solving the min-max optimization problem for training…
In this paper, we propose and analyze a set of fully non-stationary Anderson acceleration algorithms with dynamic window sizes and optimized damping. Although Anderson acceleration (AA) has been used for decades to speed up nonlinear…