Francis R. Bach

Tree-dependent Component Analysis

We present a generalization of independent component analysis (ICA), where instead of looking for a linear transform that makes the data components independent, we look for a transform that makes...

Weakly-Supervised Alignment of Video with Text

Non-local sparse models for image restoration

Automatic annotation of human actions in video

Ask the locals: Multi-way local pooling for image recognition

Finding Actors and Actions in Movies

Structured Penalties for Log-Linear Language Models

Structured Sparsity and Convex Optimization

Fast Rates for Structured Prediction

Averaging Stochastic Gradient Descent on Riemannian Manifolds

An uncertainty principle for Linear Recurrent Neural Networks

A Dimension-free Computational Upper-bound for Smooth Optimal Transport Estimation

From Averaging to Acceleration, There is Only a Step-size

Sharp analysis of low-rank kernel matrix approximations

Beyond Least-Squares: Fast Rates for Regularized Empirical Risk Minimization through Self-Concordance

Kernelized Diffusion Maps

Stochastic Composite Least-Squares Regression with Convergence Rate $O(1/n)$

Physics-informed machine learning as a kernel method