Machine Learning Research Blog francisbach.com

Closed-form dynamics beyond quadratics – Machine Learning Research Blog

francisbach.com·10w

Beyond Power Laws: Scaling Laws for Next-Token Prediction

francisbach.com·33w·Hacker News

Revisiting scaling laws via the z-transform

francisbach.com·43w

Unraveling spectral properties of kernel matrices – II

francisbach.com·60w

Learning Theory from First Principles

francisbach.com·71w·Hacker News

Scaling Laws of Optimization

francisbach.com·84w

Unraveling spectral properties of kernel matrices – I

francisbach.com·123w

Revisiting the classics: Jensen’s inequality

francisbach.com·166w

Non-convex quadratic optimization problems

francisbach.com·171w

Discrete, continuous and continuized accelerations

francisbach.com·178w

Sums-of-squares for dummies: a view from the Fourier domain

francisbach.com·182w

Rethinking SGD’s noise – II: Implicit Bias

francisbach.com·191w

Rethinking SGD’s noise

francisbach.com·199w

Information theory with kernel methods

francisbach.com·215w

Log in to enable infinite scrolling