Roman Pogodin

Publication Activity (10 Years)

Years Active: 2017-2024
Publications (10 Years): 16

Top Topics

Invariant Representation

Hebbian Learning

Recurrent Neural Networks

Conditional Independence

Top Venues

Publications

Roman Pogodin, Antonin Schrab, Yazhe Li, Danica J. Sutherland, Arthur Gretton
Practical Kernel Tests of Conditional Independence. CoRR (2024)
Roman Pogodin, Jonathan Cornford, Arna Ghosh, Gauthier Gidel, Guillaume Lajoie, Blake Aaron Richards
Synaptic Weight Distributions Depend on the Geometry of Plasticity. ICLR (2024)
Roman Pogodin, Jonathan Cornford, Arna Ghosh, Gauthier Gidel, Guillaume Lajoie, Blake A. Richards
Synaptic Weight Distributions Depend on the Geometry of Plasticity. CoRR (2023)
Roman Pogodin, Namrata Deka, Yazhe Li, Danica J. Sutherland, Victor Veitch, Arthur Gretton
Efficient Conditionally Invariant Representation Learning. ICLR (2023)
Roman Pogodin, Namrata Deka, Yazhe Li, Danica J. Sutherland, Victor Veitch, Arthur Gretton
Efficient Conditionally Invariant Representation Learning. CoRR (2022)
Roman Pogodin, Yash Mehta, Timothy P. Lillicrap, Peter E. Latham
Towards Biologically Plausible Convolutional Networks. CoRR (2021)
Roman Pogodin, Yash Mehta, Timothy P. Lillicrap, Peter E. Latham
Towards Biologically Plausible Convolutional Networks. NeurIPS (2021)
Yazhe Li, Roman Pogodin, Danica J. Sutherland, Arthur Gretton
Self-Supervised Learning with Kernel Dependence Maximization. NeurIPS (2021)
Yazhe Li, Roman Pogodin, Danica J. Sutherland, Arthur Gretton
Self-Supervised Learning with Kernel Dependence Maximization. CoRR (2021)
Roman Pogodin, Peter E. Latham
Kernelized information bottleneck leads to biologically plausible 3-factor Hebbian learning in deep networks. CoRR (2020)
Roman Pogodin, Peter E. Latham
Kernelized information bottleneck leads to biologically plausible 3-factor Hebbian learning in deep networks. NeurIPS (2020)
Roman Pogodin, Tor Lattimore
On First-Order Bounds, Variance and Gap-Dependent Bounds for Adversarial Bandits. UAI (2019)
Roman Pogodin, Dane S. Corneil, Alexander Seeholzer, Joseph Heng, Wulfram Gerstner
Working memory facilitates reward-modulated Hebbian learning in recurrent neural networks. CoRR (2019)
Roman Pogodin, Tor Lattimore
Adaptivity, Variance and Separation for Adversarial Bandits. CoRR (2019)
Roman Pogodin, Mikhail Krechetov, Yury Maximov
Efficient rank minimization to tighten semidefinite programming for unconstrained binary quadratic optimization. Allerton (2017)
Roman Pogodin, Mikhail Krechetov, Yury Maximov
Efficient Rank Minimization to Tighten Semidefinite Programming for Unconstrained Binary Quadratic Optimization. CoRR (2017)