22 citations · 57 across the 9 of their papers we have counts for
5 papers · 1 filter
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…
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…
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…
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…