AIConfPaper
← Search

Roman Pogodin

8 accepted papers

2026

Learning From the Past with Cascading Eligibility Traces

Tokiniaina Raharison Ralambomihanta, Ivan Anokhin, Roman Pogodin, Samira Ebrahimi Kahou, Jonathan Cornford, Blake Aaron Richards
ICLR 2026poster

Animals often receive information about errors and rewards after significant delays. In some cases these delays are fixed aspects of neural processing or sensory feedback, for example, there is typically a delay of tens to hundreds of milliseconds between motor actions and visual feedback. The stand…

Cited by 0Source ↗code ↗Scholar ↗
2025

On the Hardness of Conditional Independence Testing In Practice

Zheng He, Roman Pogodin, Yazhe Li, Namrata Deka, Arthur Gretton, Danica J. Sutherland
NeurIPS 2025spotlight

Tests of conditional independence (CI) underpin a number of important problems in machine learning and statistics, from causal discovery to evaluation of predictor fairness and out-of-distribution robustness. Shah and Peters (2020) showed that, contrary to the unconditional case, no universally fini…

Cited by 0Source ↗Scholar ↗
2024

Synaptic Weight Distributions Depend on the Geometry of Plasticity

Roman Pogodin, Jonathan Cornford, Arna Ghosh, Gauthier Gidel, Guillaume Lajoie, Blake Aaron Richards
ICLR 2024spotlight

A growing literature in computational neuroscience leverages gradient descent and learning algorithms that approximate it to study synaptic plasticity in the brain. However, the vast majority of this work ignores a critical underlying assumption: the choice of distance for synaptic changes - i.e. th…

Cited by 6Source ↗PDF ↗code ↗Scholar ↗
2023

Efficient Conditionally Invariant Representation Learning

Roman Pogodin, Namrata Deka, Yazhe Li, Danica J. Sutherland, Victor Veitch, Arthur Gretton
ICLR 2023top-5%

We introduce the Conditional Independence Regression CovariancE (CIRCE), a measure of conditional independence for multivariate continuous-valued variables. CIRCE applies as a regularizer in settings where we wish to learn neural features $\varphi(X)$ of data $X$ to estimate a target $Y$, while bein…

Cited by 20Source ↗PDF ↗code ↗Scholar ↗
2021

Self-Supervised Learning with Kernel Dependence Maximization

Yazhe Li, Roman Pogodin, Danica J. Sutherland, Arthur Gretton
NeurIPS 2021poster

We approach self-supervised learning of image representations from a statistical dependence perspective, proposing Self-Supervised Learning with the Hilbert-Schmidt Independence Criterion (SSL-HSIC). SSL-HSIC maximizes dependence between representations of transformations of an image and the image i…

Cited by 88Source ↗PDF ↗code ↗Scholar ↗
2021

Towards Biologically Plausible Convolutional Networks

Roman Pogodin, Yash Mehta, Timothy P Lillicrap, Peter E. Latham
NeurIPS 2021poster

Convolutional networks are ubiquitous in deep learning. They are particularly useful for images, as they reduce the number of parameters, reduce training time, and increase accuracy. However, as a model of the brain they are seriously problematic, since they require weight sharing - something real n…

Cited by 35Source ↗PDF ↗code ↗Scholar ↗
2020

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

Roman Pogodin, Peter E. Latham
NeurIPS 2020poster

The state-of-the art machine learning approach to training deep neural networks, backpropagation, is implausible for real neural networks: neurons need to know their outgoing weights; training alternates between a bottom-up forward pass (computation) and a top-down backward pass (learning); and the…

Cited by 50Source ↗PDF ↗code ↗Scholar ↗