67 citations · 70 across the 5 of their papers we have counts for
7 papers
Temporal Recurrence Favors Fewer Layers
Ivan Anokhin, Johan Obando-Ceron, Irina Rish +1
In streaming tasks, recurrent models can carry latent computation across time, allowing each update to build on representations produced earlier. This raises a basic question: once…
Learning From the Past with Cascading Eligibility Traces
Tokiniaina Raharison Ralambomihanta, Ivan Anokhin, Roman Pogodin +3
Animals often receive information about errors and rewards after a significant delay. For example, there is typically a delay of tens to hundreds of milliseconds between motor acti…
Thinker: Learning to Plan and Act
Stephen Chung, Ivan Anokhin, David Krueger
We propose the Thinker algorithm, a novel approach that enables reinforcement learning agents to autonomously interact with and utilize a learned world model. The Thinker algorithm…
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…
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…
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…
High-Resolution Daytime Translation Without Domain Labels
Ivan Anokhin, Pavel Solovev, Denis Korzhenkov +6
Modeling daytime changes in high resolution photographs, e.g., re-rendering the same scene under different illuminations typical for day, night, or dawn, is a challenging image man…