Related papers: Geoff: The Generic Optimization Framework & Fronte…
We examine popular gradient-based algorithms for nonlinear control in the light of the modern complexity analysis of first-order optimization algorithms. The examination reveals that the complexity bounds can be clearly stated in terms of…
While Model Predictive Control (MPC) delivers strong performance across robotics applications, solving the underlying (batches of) nonlinear trajectory optimization (TO) problems online remains computationally demanding. Existing…
Parallel accelerators, such as GPUs, are key enablers for large-scale Machine Learning (ML) applications. However, ML model developers often lack detailed knowledge of the underlying system architectures, while system programmers usually do…
PYROBOCOP is a Python-based package for control, optimization and estimation of robotic systems described by nonlinear Differential Algebraic Equations (DAEs). In particular, the package can handle systems with contacts that are described…
Automated Feature Engineering (AFE) refers to automatically generate and select optimal feature sets for downstream tasks, which has achieved great success in real-world applications. Current AFE methods mainly focus on improving the…
We implement a quantum optimal control algorithm based on automatic differentiation and harness the acceleration afforded by graphics processing units (GPUs). Automatic differentiation allows us to specify advanced optimization criteria and…
The US National Gemini Office (US NGO), part of the Community Science and Data Center (CSDC) at NSF's NOIRLab, has completed a project to upgrade the IRAF-based Gemini reduction software to provide a fully supported system capable of…
Recent advances in feature learning have shown that self-supervised vision foundation models can capture semantic correspondences but often lack awareness of underlying 3D geometry. GECO addresses this gap by producing geometrically…
We present a Python package together with a practical guide for the implementation of a lightweight diversity-enhanced genetic algorithm (GA) approach for the exploration of multi-dimensional parameter spaces. Searching a parameter space…
In this paper we introduce DISROPT, a Python package for distributed optimization over networks. We focus on cooperative set-ups in which an optimization problem must be solved by peer-to-peer processors (without central coordinators) that…
There are plenty of graph neural network (GNN) accelerators being proposed. However, they highly rely on users' hardware expertise and are usually optimized for one specific GNN model, making them challenging for practical use. Therefore,…
GEANT4 is a particle physics simulation tool used to develop and optimize radiation detectors. While C++ based examples exist, Python's growing popularity necessitates the development of a more accessible Python bindings interface. This…
In this paper, we present the Fast Optimizer Benchmark (FOB), a tool designed for evaluating deep learning optimizers during their development. The benchmark supports tasks from multiple domains such as computer vision, natural language…
In recent years, architectures combining a reconfigurable fabric and a general purpose processor on a single chip became increasingly popular. Such hybrid architectures allow extending embedded software with application specific hardware…
The ATLAS collaboration defines methods, establishes procedures, and organises advisory groups to manage the publication processes of scientific papers, conference papers, and public notes. All stages are managed through web systems,…
A Particle Flow Algorithm (PFA) with the minimized dependence on the detector geometry is presented. Current PFA implementation includes procedures of the track reconstruction, calorimeter clustering, and individual particle reconstruction…
Particle filters are a class of algorithms that are used for "tracking" or "filtering" in real-time for a wide array of time series models. Despite their comprehensive applicability, particle filters are not always the tool of choice for…
Effector is a Python package for interpreting machine learning (ML) models that are trained on tabular data through global and regional feature effects. Global effects, like Partial Dependence Plot (PDP) and Accumulated Local Effects (ALE),…
Existing GPU libraries often struggle to fully exploit the parallel resources and on-chip memory (SRAM) of GPUs when chaining multiple GPU functions as individual kernels. While Kernel Fusion (KF) techniques like Horizontal Fusion (HF) and…
The evaluation of clustering algorithms can involve running them on a variety of benchmark problems, and comparing their outputs to the reference, ground-truth groupings provided by experts. Unfortunately, many research papers and graduate…