Roman Pogodin
6 papers · 2019–2024 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Bronze π Academic Marathon Β· Sprint πΊοΈ Taxonomy Completionist (17) π£ Hot Topic Early Bird π Conference Polyglot Β· Bronze
π
Keyword Champion
(2)
π
Conference Pioneer
Venues
Top co-authors
Research topics
Machine Learning
(6)
Optimization & Theory
(4)
Deep Learning
(2)
Interdisciplinary
(2)
Core Methods
(2)
Learning Types Β· Machine Learning
(2)
Science
(2)
Computer Vision
(1)
Mathematics & Optimization
(1)
Application Areas
(1)
Architectures
(1)
Cognitive Science
(1)
Core AI
(1)
Learning Types Β· Deep Learning
(1)
Optimization
(1)
Keywords
biological plausibility
(2)
kernel methods
(2)
representation learning
(2)
computational neuroscience
(1)
information bottleneck
(1)
self-supervised learning
(1)
regret minimization
(1)
mutual information
(1)
hebbian learning
(1)
gradient descent
(1)
synaptic plasticity
(1)
hilbert-schmidt independence criterion
(1)
divisive normalization
(1)
mirror descent
(1)
image representation
(1)
weight sharing
(1)
lateral connectivity
(1)
conditional independence
(1)
synaptic weight distributions
(1)
hebbian plasticity
(1)
Papers
Synaptic Weight Distributions Depend on the Geometry of Plasticity
ICLR 2024
Efficient Conditionally Invariant Representation Learning
ICLR 2023
Self-Supervised Learning with Kernel Dependence Maximization
NeurIPS 2021
Towards Biologically Plausible Convolutional Networks
NeurIPS 2021
Kernelized information bottleneck leads to biologically plausible 3-factor Hebbian learning in deep networks
NeurIPS 2020
On First-Order Bounds, Variance and Gap-Dependent Bounds for Adversarial Bandits
UAI 2019