13 citations · 60 across the 31 of their papers we have counts for
4 papers · 1 filter
Binary Search with Distributional Predictions
Michael Dinitz, Sungjin Im, Thomas Lavastida +3
Algorithms with (machine-learned) predictions is a powerful framework for combining traditional worst-case algorithms with modern machine learning. However, the vast majority of wo…
Algorithms with Prediction Portfolios
Michael Dinitz, Sungjin Im, Thomas Lavastida +2
The research area of algorithms with predictions has seen recent success showing how to incorporate machine learning into algorithm design to improve performance when the predictio…
Faster Matchings via Learned Duals
Michael Dinitz, Sungjin Im, Thomas Lavastida +2
A recent line of research investigates how algorithms can be augmented with machine-learned predictions to overcome worst case lower bounds. This area has revealed interesting algo…
On Coresets for Regularized Loss Minimization
Ryan R. Curtin, Sungjin Im, Ben Moseley +2
We design and mathematically analyze sampling-based algorithms for regularized loss minimization problems that are implementable in popular computational models for large data, in…