activity
20142026
most citedTowards Deep Learning Models Resistant to Adversarial Attacks

1.5k citations · 1.6k across the 23 of their papers we have counts for

collaborators
Showing 2023Show all

2 papers · 1 filter

cs.DS2023

Interior Point Methods with a Gradient Oracle

Adrian Vladu

We provide an interior point method based on quasi-Newton iterations, which only requires first-order access to a strongly self-concordant barrier function. To achieve this, we ext…

cs.LG2023★ 5 cited

Quantized Distributed Training of Large Models with Convergence Guarantees

Ilia Markov, Adrian Vladu, Qi Guo +1

Communication-reduction techniques are a popular way to improve scalability in data-parallel training of deep neural networks (DNNs). The recent emergence of large language models…