154 citations · 861 across the 94 of their papers we have counts for
8 papers · 1 filter
Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks
Xiangyu Chang, Yingcong Li, Samet Oymak +1
Deep networks are typically trained with many more parameters than the size of the training dataset. Recent empirical evidence indicates that the practice of overparameterization n…
On the Marginal Benefit of Active Learning: Does Self-Supervision Eat Its Cake?
Yao-Chun Chan, Mingchen Li, Samet Oymak
Active learning is the set of techniques for intelligently labeling large unlabeled datasets to reduce the labeling effort. In parallel, recent developments in self-supervised and…
Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic View
Christos Thrampoulidis, Samet Oymak, Mahdi Soltanolkotabi
Contemporary machine learning applications often involve classification tasks with many classes. Despite their extensive use, a precise understanding of the statistical properties…
Unsupervised Paraphrasing via Deep Reinforcement Learning
A. B. Siddique, Samet Oymak, Vagelis Hristidis
Paraphrasing is expressing the meaning of an input sentence in different wording while maintaining fluency (i.e., grammatical and syntactical correctness). Most existing work on pa…
Statistical and Algorithmic Insights for Semi-supervised Learning with Self-training
Samet Oymak, Talha Cihad Gulcu
Self-training is a classical approach in semi-supervised learning which is successfully applied to a variety of machine learning problems. Self-training algorithm generates pseudo-…
Exploring Weight Importance and Hessian Bias in Model Pruning
Mingchen Li, Yahya Sattar, Christos Thrampoulidis +1
Model pruning is an essential procedure for building compact and computationally-efficient machine learning models. A key feature of a good pruning algorithm is that it accurately…