Parallel computing, algorithms, programming languages, machine learning, and natural language processing.
I'm going to be ruthless. Put your bulletproof vest on.
SC 2024 · Atlanta
Cédric Augonnet, Andrei Alexandrescu, Albert Sidelnik, and Michael Garland.
Organizing computation as asynchronous tasks with data-driven dependencies is a simple and efficient model for single- and multi-GPU programs.
HOPL IV, 2020 (held in 2021)
Walter Bright, Andrei Alexandrescu, and Michael Parker.
As its name suggests, the initial motivation for the D programming language was to improve on C and C++ while keeping their spirit.
SEA 2017 · King's College London
The selection algorithm Median of Medians, although a landmark theoretical achievement, is seldom used in practice because it is slower than simple approaches based on sampling.
Interspeech 2011
Katrin Kirchhoff and Andrei Alexandrescu.
Graph-based learners in particular utilize an objective function that not only maximizes the classification accuracy on a labeled set but also the global smoothness of the predicted label assignment.
PhD dissertation · University of Washington, 2009
Graph-based semi-supervised learning techniques have recently attracted increasing attention as a means to utilize unlabeled data in machine learning by placing data points in a similarity graph.
NAACL HLT 2009
Andrei Alexandrescu and Katrin Kirchhoff.
Current phrase-based statistical machine translation systems process each test sentence in isolation and do not enforce global consistency constraints, even though the test data is often internally consistent with respect to topic or style.
IEEE ASRU 2007
Andrei Alexandrescu and Katrin Kirchhoff.
We introduce graph-based learning for acoustic-phonetic classification.
HLT-NAACL 2007
Andrei Alexandrescu and Katrin Kirchhoff.
The problem of how to best construct this graph remains largely unsolved.
HLT-NAACL 2006
Andrei Alexandrescu and Katrin Kirchhoff.
We present a new type of neural probabilistic language model that learns a mapping from both words and explicit word features into a continuous space that is then used for word prediction.
UW EE Technical Report UWEETR-2006-0014
Andrei Alexandrescu and Katrin Kirchhoff. Technical-report version of the NAACL paper.
Language models based on a continuous word representation and neural network probability estimation have recently emerged as an alternative to the established backoff language models.