22 citations · 57 across the 9 of their papers we have counts for
11 papers
On the Hardness of Conditional Independence Testing In Practice
Zheng He, Roman Pogodin, Yazhe Li +3
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…
Practical Kernel Tests of Conditional Independence
Roman Pogodin, Antonin Schrab, Yazhe Li +2
We describe a data-efficient, kernel-based approach to statistical testing of conditional independence. A major challenge of conditional independence testing is to obtain the corre…
Synaptic Weight Distributions Depend on the Geometry of Plasticity
Roman Pogodin, Jonathan Cornford, Arna Ghosh +3
A growing literature in computational neuroscience leverages gradient descent and learning algorithms that approximate it to study synaptic plasticity in the brain. However, the va…
Efficient Conditionally Invariant Representation Learning
Roman Pogodin, Namrata Deka, Yazhe Li +3
We introduce the Conditional Independence Regression CovariancE (CIRCE), a measure of conditional independence for multivariate continuous-valued variables. CIRCE applies as a regu…
Towards Biologically Plausible Convolutional Networks
Roman Pogodin, Yash Mehta, Timothy P. Lillicrap +1
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 accurac…
Self-Supervised Learning with Kernel Dependence Maximization
Yazhe Li, Roman Pogodin, Danica J. Sutherland +1
We approach self-supervised learning of image representations from a statistical dependence perspective, proposing Self-Supervised Learning with the Hilbert-Schmidt Independence Cr…
Kernelized information bottleneck leads to biologically plausible 3-factor Hebbian learning in deep networks
Roman Pogodin, Peter E. Latham
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 weigh…
Working memory facilitates reward-modulated Hebbian learning in recurrent neural networks
Roman Pogodin, Dane Corneil, Alexander Seeholzer +2
Reservoir computing is a powerful tool to explain how the brain learns temporal sequences, such as movements, but existing learning schemes are either biologically implausible or t…
On First-Order Bounds, Variance and Gap-Dependent Bounds for Adversarial Bandits
Roman Pogodin, Tor Lattimore
We make three contributions to the theory of k-armed adversarial bandits. First, we prove a first-order bound for a modified variant of the INF strategy by Audibert and Bubeck [200…
Efficient Rank Minimization to Tighten Semidefinite Programming for Unconstrained Binary Quadratic Optimization
Roman Pogodin, Mikhail Krechetov, Yury Maximov
We propose a method for low-rank semidefinite programming in application to the semidefinite relaxation of unconstrained binary quadratic problems. The method improves an existing…
Quadratic Programming Approach to Fit Protein Complexes into Electron Density Maps
Roman Pogodin, Alexander Katrutsa, Sergei Grudinin
The paper investigates the problem of fitting protein complexes into electron density maps. They are represented by high-resolution cryoEM density maps converted into overlapping m…