no code implementations • 25 Nov 2022 • Hatem Helal, Jesun Firoz, Jenna Bilbrey, Mario Michael Krell, Tom Murray, Ang Li, Sotiris Xantheas, Sutanay Choudhury
Molecular property calculations are the bedrock of chemical physics.
no code implementations • 14 Sep 2022 • Mario Michael Krell, Manuel Lopez, Sreenidhi Anand, Hatem Helal, Andrew William Fitzgibbon
However, the sizes of small graphs can vary substantially with respect to the number of nodes and edges, and hence the size of the combined graph can still vary considerably, especially for small batch sizes.
no code implementations • 10 Aug 2022 • Mario Michael Krell, Nils Wilshusen, Anett Seeland, Su Kyoung Kim
Adding all and removing the oldest samples results in the best performance, whereas for smaller drifts, it can be sufficient to only add potential new support vectors of the SVM which reduces processing resources.
no code implementations • 29 Sep 2021 • Matej Kosec, Sheng Fu, Mario Michael Krell
The shortest-pack-first histogram-packing (SPFHP) algorithm determines the packing order for the Wikipedia dataset of over 16M sequences in 0. 02 seconds.
no code implementations • 24 Sep 2021 • Edward H. Lee, Mario Michael Krell, Alexander Tsyplikhin, Victoria Rege, Errol Colak, Kristen W. Yeom
We also provide two extensions: 1) DPSGD for pipelined models and 2) per-layer clipping that is 15x faster than the Opacus implementation on 8x A100s.
1 code implementation • NeurIPS 2021 • Mario Michael Krell, Matej Kosec, Sergio P. Perez, Andrew Fitzgibbon
We show in this paper that the variation in sequence lengths in common NLP datasets is such that up to 50% of all tokens can be padding.
1 code implementation • 14 Jan 2021 • Daniel Ma, Gerald Friedland, Mario Michael Krell
Origami is becoming more and more relevant to research.
1 code implementation • 23 Dec 2020 • Sourabh Kulkarni, Mario Michael Krell, Seth Nabarro, Csaba Andras Moritz
The statistical inference framework is implemented and compared on Intel Xeon CPU, NVIDIA Tesla V100 GPU and the Graphcore Mk1 IPU, and the results are discussed in the context of their computational architectures.
1 code implementation • 12 Dec 2020 • Sourabh Kulkarni, Alexander Tsyplikhin, Mario Michael Krell, Csaba Andras Moritz
As a proof-of-concept, we demonstrate inference over a probabilistic epidemiology model used to predict the spread of COVID-19.
no code implementations • 10 Sep 2020 • Mario Michael Krell, Bilal Wehbe
We show on synthetic and robotic data in reproducible experiments that classical metrics behave wrongly, whereas our new metrics are less sensitive to changing distributions, especially when correcting by the marginal distribution in $X$.
no code implementations • 17 Sep 2018 • Bilal Wehbe, Octavio Arriaga, Mario Michael Krell, Frank Kirchner
Multi-context model learning is crucial for marine robotics where several factors can cause disturbances to the system's dynamics.
no code implementations • 15 Jan 2018 • Mario Michael Krell
The classification of complex data usually requires the composition of processing steps.
no code implementations • 9 Jan 2018 • Mario Michael Krell, Anett Seeland, Su Kyoung Kim
On image data, data augmentation is becoming less relevant due to the large amount of available training data and regularization techniques.