Papers

. Optimal mini-batch and step sizes for SAGA, to appear in ICML 2019.

Preprint Code

SGD: general analysis and improved rates, to appear in ICML 2019.

Preprint

. Characterising particulate random media from near-surface backscattering: A machine learning approach to predict particle size and concentration . EPL (Europhysics Letters), 2018.

Preprint Project Paper Journal

Improving SAGA via a probabilistic interpolation with gradient descent, 2018.

Preprint

Stochastic quasi-gradient methods: variance reduction via Jacobian sketching, 2018.

Preprint Code

Accelerated stochastic matrix inversion: general theory and speeding up BFGS rules for faster second-order optimization, NIPS, 2018.

Preprint Code Proceedings Poster

Greedy stochastic algorithms for entropy-regularized optimal transport problems, AISTATS, 2018.

Preprint Proceedings Poster

Tracking the gradients using the Hessian: A new look at variance reducing stochastic methods, AISTATS (Oral presenation), 2018.

Preprint Code Proceedings Slides Poster

Randomized quasi-Newton updates are linearly convergent matrix inversion algorithms, SIAM Journal on Matrix Analysis and Applications, 2017.

Preprint Code Journal Slides

Linearly Convergent Randomized Iterative Methods for Computing the Pseudoinverse, 2016.

Preprint Code Slides

Sketch and Project: Randomized Iterative Methods for Linear Systems and Inverting Matrices, PhD Dissertation, School of Mathematics, The University of Edinburgh, 2016.

Preprint Code Slides

Stochastic Block BFGS: Squeezing More Curvature out of Data, ICML, 2016.

Preprint Code Proceedings Slides Poster

Stochastic dual ascent for solving linear systems, 2015.

Preprint Code

Randomized iterative methods for linear systems, SIAM Journal on Matrix Analysis and Applications, 2015.

Preprint Journal Slides Code Most downloaded on SIMAX

High order reverse automatic differentiation with emphasis on the third order, Mathematical Programming, 2014.

Preprint Journal Slides Code

Computing the sparsity pattern of Hessians using automatic differentiation, ACM Transactions on Mathematical Software, 2014.

Preprint Journal Code

A new framework for Hessian automatic differentiation, Optimization Methods and Software, 2012.

Preprint Journal Code

Recent & Upcoming Talks

ICCOPT 2019
Aug 5, 2019
Expected smoothness is the key to understanding the mini-batch complexity of stochastic gradient methods

Teaching

African Masters of Machine Intelligence (AMMI) (Winter 2019)

1) Lecture I: Introduction into ML and optimization
2) Exercises on convexity, smoothness and gradient descent
3) Lecture II: proximal gradient methods
4) Exercises on proximal operator
5) Lecture III: Stochastic gradient descent
6) Exercises on stochastc methods
7) Lecture IV: Stochastic variance reduced gradient methods
8) Notes on stochastic variance reduced methods

MDI210 Optimization et Analise númeric (Summer 2018)

Here are some good lecture notes on Linear Programming by Marco Chiarandini. Here are my lecture notes (WARNING: these notes are a work in progress!)
1) numerical linear algebra
2) nonlinear optimization
3) My lecture slides on Linear Programming

Master2 Optimization for Data Science (2018/2019)

Lecture slides:
1) intro ML
2) convexity and smoothness
3) proximity operator, ISTA and FISTA.

Lecture notes on gradient descent proofs.

Exercises:
1) convexity and smoothness, (with answers)
3) GD and SGD on linear least squares, (with answers)
4) gradient descent and Ridge Regression, (with answers)
5) proximity operator, (with answers)

Contact

Nerv Symbol

  • gowerrobert$@$gmail.com
  • Télécom ParisTech, 46 Rue Barrault, 75634 Paris Cedex 13, France Office: E 409
  • email for appointment