MIT Open Access Articles: Recent submissions
Now showing items 22-24 of 53091
-
MLTCP: A Distributed Technique to Approximate Centralized Flow Scheduling For Machine Learning
(ACM|The 23rd ACM Workshop on Hot Topics in Networks, 2024-11-18)This paper argues that congestion control protocols in machine learning datacenters sit at a sweet spot between centralized and distributed flow scheduling solutions. We present MLTCP, a technique to augment today's ... -
Imaging the initial condition of heavy-ion collisions and nuclear structure across the nuclide chart
(Springer Nature Singapore, 2024-12-11)High-energy nuclear collisions encompass three key stages: the structure of the colliding nuclei, informed by low-energy nuclear physics, the initial condition, leading to the formation of quark–gluon plasma (QGP), and the ... -
Anomaly-aware summary statistic from data batches
(Springer Berlin Heidelberg, 2024-12-12)Signal-agnostic data exploration based on machine learning could unveil very subtle statistical deviations of collider data from the expected Standard Model of particle physics. The beneficial impact of a large training ...