2 citations · 2 across the 2 of their papers we have counts for
3 papers
stat.ML2022
Embedded Ensembles: Infinite Width Limit and Operating Regimes
Maksim Velikanov, Roman Kail, Ivan Anokhin +4
A memory efficient approach to ensembling neural networks is to share most weights among the ensembled models by means of a single reference network. We refer to this strategy as E…
cs.CV2020
Image Generators with Conditionally-Independent Pixel Synthesis
Ivan Anokhin, Kirill Demochkin, Taras Khakhulin +3
Existing image generator networks rely heavily on spatial convolutions and, optionally, self-attention blocks in order to gradually synthesize images in a coarse-to-fine manner. He…
cs.LG2020★ 2 cited
Low-loss connection of weight vectors: distribution-based approaches
Ivan Anokhin, Dmitry Yarotsky
Recent research shows that sublevel sets of the loss surfaces of overparameterized networks are connected, exactly or approximately. We describe and compare experimentally a panel…