On Information Theoretic Bounds for SGD · April 23, 2021 · generalization information theory

Notes on the Origin of Implicit Regularization in SGD · April 1, 2021 · deep learning generalization SGD differerntial equations

An information maximization view on the $\beta$-VAE objective · March 18, 2021 · VAE generative models deep learning KL divergence

Some Intuition on the Neural Tangent Kernel · November 20, 2020

Notes on Causally Correct Partial Models · November 12, 2020

Meta-Learning Millions of Hyper-parameters using the Implicit Function Theorem · November 14, 2019

The secular Bayesian: Using belief distributions without really believing · October 31, 2019

Exponentially Growing Learning Rate? Implications of Scale Invariance induced by Batch Normalization · October 25, 2019

On Marginal Likelihood and Cross-Validation · October 17, 2019

Notes on iMAML: Meta-Learning with Implicit Gradients · September 19, 2019