Algorithms - Microsoft Research

Publication

uGLAD: A Deep Learning Model to Recover Conditional Independence Graphs

Harsh Shrivastava, Urszula Chajewska, Robin Abraham, Xinshi Chen

Workshop on New Frontiers in Graph Learning (NeurIPS 2022) | December 2022

Groupe

Microsoft Research Special Projects

Note: This research has reached its conclusion, and this page is for historical reference and archival purposes only. The Microsoft Research Special Projects group operates on the boundary between engineering and research to drive breakthrough…

Publication

Improved Field Size Bounds for Higher Order MDS Codes

Joshua Brakensiek, Manik Dhar, Sivakanth Gopi

ISIT 2023 | December 2022

Publication

A construction of Maximally Recoverable LRCs for small number of local groups

Manik Dhar, Sivakanth Gopi

ISIT 2023 | December 2022

Publication

Near-Optimal Correlation Clustering with Privacy

Vincent Cohen-Addad, Chenglin Fan, Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Nikos Parotsidis, Jakub Tarnawski

NeurIPS 2022 | November 2022

Projet

Publication

Differentially Private Model Compression

Fatemehsadat Mireshghallah, Arturs Backurs, Huseyin Inan, Lukas Wutschitz, Janardhan (Jana) Kulkarni

NeurIPS 2022 | November 2022

Projet

Publication

An ensemble of VisNet, Transformer-M, and pretraining models for molecular property prediction in OGB Large-Scale Challenge@ NeurIPS 2022

Yusong Wang, Shaoning Li, Tong Wang, Zun Wang, Xinheng He, Bin Shao, Tie-Yan Liu

MSR-TR-2022-35 | November 2022

Publié par Microsoft

Competition Winner

Publication

When does differentially private learning not suffer in high dimensions?

Xuechen Li, Daogao Liu, Tatsunori Hashimoto, Huseyin Inan, Janardhan (Jana) Kulkarni, Yin Tat Lee, Abhradeep Guha Thakurta

NeurIPS’22 | November 2022

Projet

Groupe

ML robuste, adaptatif et modulaire | Montréal

Notre objectif est de comprendre les principes qui sous-tendent l’apprentissage et la généralisation, afin de créer des systèmes d’IA fiables capables d’apprendre plus efficacement à partir des données disponibles, de collecter intelligemment des données pertinentes…

Publication

Low-depth arithmetic circuit lower bounds via shifted partials

Prashanth Amireddy, Ankit Garg, Neeraj Kayal, Chandan Saha, Bhargav Thankey

Electronic Colloquium on Computational Complexity, 2022 | November 2022