45 citations · 85 across the 8 of their papers we have counts for
8 papers
LLM-Pilot: Characterize and Optimize Performance of your LLM Inference Services
Małgorzata Łazuka, Andreea Anghel, Thomas Parnell
As Large Language Models (LLMs) are rapidly growing in popularity, LLM inference services must be able to serve requests from thousands of users while satisfying performance requir…
Graph Feature Preprocessor: Real-time Subgraph-based Feature Extraction for Financial Crime Detection
Jovan Blanuša, Maximo Cravero Baraja, Andreea Anghel +4
In this paper, we present "Graph Feature Preprocessor", a software library for detecting typical money laundering patterns in financial transaction graphs in real time. These patte…
Search-based Methods for Multi-Cloud Configuration
Małgorzata Łazuka, Thomas Parnell, Andreea Anghel +1
Multi-cloud computing has become increasingly popular with enterprises looking to avoid vendor lock-in. While most cloud providers offer similar functionality, they may differ sign…
SnapBoost: A Heterogeneous Boosting Machine
Thomas Parnell, Andreea Anghel, Malgorzata Lazuka +5
Modern gradient boosting software frameworks, such as XGBoost and LightGBM, implement Newton descent in a functional space. At each boosting iteration, their goal is to find the ba…
Breadth-first, Depth-next Training of Random Forests
Andreea Anghel, Nikolas Ioannou, Thomas Parnell +3
In this paper we analyze, evaluate, and improve the performance of training Random Forest (RF) models on modern CPU architectures. An exact, state-of-the-art binary decision tree b…
Sampling Acquisition Functions for Batch Bayesian Optimization
Alessandro De Palma, Celestine Mendler-Dünner, Thomas Parnell +2
We present Acquisition Thompson Sampling (ATS), a novel technique for batch Bayesian Optimization (BO) based on the idea of sampling multiple acquisition functions from a stochasti…
Benchmarking and Optimization of Gradient Boosting Decision Tree Algorithms
Andreea Anghel, Nikolaos Papandreou, Thomas Parnell +2
Gradient boosting decision trees (GBDTs) have seen widespread adoption in academia, industry and competitive data science due to their state-of-the-art performance in many machine…
Snap ML: A Hierarchical Framework for Machine Learning
Celestine Dünner, Thomas Parnell, Dimitrios Sarigiannis +5
We describe a new software framework for fast training of generalized linear models. The framework, named Snap Machine Learning (Snap ML), combines recent advances in machine learn…