Roman Pogodin
6 papers · 2019–2024 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (15) π§ Keyword Pioneer π Conference Polyglot (3) π Academic Marathon (5) π Cross-Pollinator (6)
π
Renaissance Researcher
(5)
π
Interdisciplinary Bridge
π
Conference Pioneer
Conferences
NIPS (3)
ICLR (2)
UAI (1)
Top co-authors
Keywords
kernel methods
(2)
biological plausibility
(2)
information bottleneck
(1)
self-supervised learning
(1)
regret minimization
(1)
mutual information
(1)
hebbian learning
(1)
hilbert-schmidt independence criterion
(1)
divisive normalization
(1)
image representation
(1)
weight sharing
(1)
lateral connectivity
(1)
hebbian plasticity
(1)
regret bound
(1)
deep neural network
(1)
convolutional network
(1)
adversarial bandit
(1)
variance analysis
(1)
follow the regularized leader
(1)
first-order bound
(1)
Papers
Synaptic Weight Distributions Depend on the Geometry of Plasticity
ICLR 2024
Efficient Conditionally Invariant Representation Learning
ICLR 2023
Towards Biologically Plausible Convolutional Networks
NIPS 2021
Self-Supervised Learning with Kernel Dependence Maximization
NIPS 2021
Kernelized information bottleneck leads to biologically plausible 3-factor Hebbian learning in deep networks
NIPS 2020
On First-Order Bounds, Variance and Gap-Dependent Bounds for Adversarial Bandits
UAI 2019