Roman Pogodin

According to our database, Roman Pogodin authored at least 11 papers between 2017 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

On the Hardness of Conditional Independence Testing In Practice.

Zheng He, Roman Pogodin, Yazhe Li, Namrata Deka, Arthur Gretton, Danica J. Sutherland

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

2024

Practical Kernel Tests of Conditional Independence.

Roman Pogodin, Antonin Schrab, Yazhe Li, Danica J. Sutherland, Arthur Gretton

CoRR, 2024

Synaptic Weight Distributions Depend on the Geometry of Plasticity.

Roman Pogodin, Jonathan Cornford, Arna Ghosh, Gauthier Gidel, Guillaume Lajoie, Blake Aaron Richards

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Efficient Conditionally Invariant Representation Learning.

Roman Pogodin, Namrata Deka, Yazhe Li, Danica J. Sutherland, Victor Veitch, Arthur Gretton

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2021

Towards Biologically Plausible Convolutional Networks.

Roman Pogodin, Yash Mehta, Timothy P. Lillicrap, Peter E. Latham

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Self-Supervised Learning with Kernel Dependence Maximization.

Yazhe Li, Roman Pogodin, Danica J. Sutherland, Arthur Gretton

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

2020

Kernelized information bottleneck leads to biologically plausible 3-factor Hebbian learning in deep networks.

Roman Pogodin, Peter E. Latham

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

2019

Working memory facilitates reward-modulated Hebbian learning in recurrent neural networks.

Roman Pogodin, Dane S. Corneil, Alexander Seeholzer, Joseph Heng, Wulfram Gerstner

CoRR, 2019

Adaptivity, Variance and Separation for Adversarial Bandits.

Roman Pogodin, Tor Lattimore

CoRR, 2019

On First-Order Bounds, Variance and Gap-Dependent Bounds for Adversarial Bandits.

Roman Pogodin, Tor Lattimore

Proceedings of the Thirty-Fifth Conference on Uncertainty in Artificial Intelligence, 2019

2017

Efficient rank minimization to tighten semidefinite programming for unconstrained binary quadratic optimization.

Roman Pogodin, Mikhail Krechetov, Yury Maximov

Proceedings of the 55th Annual Allerton Conference on Communication, 2017