Events · OBD 2015

Optimization and Big Data 2015

Workshop, trek and colloquium · 6–8 May 2015 · Edinburgh, Scotland
Informatics Forum G.07 (workshop) and JCMB (colloquium), University of Edinburgh
Organizers: Zheng Qu and Peter Richtárik
Keynote: Arkadi Nemirovski (Georgia Institute of Technology)
Original Edinburgh page · full copy

Third workshop in the series, on algorithms that scale to optimization problems with billions of variables, using distributed and parallel computing, randomization, asynchronicity, decomposition, sketching, and streaming.

Speakers

  • Arkadi Nemirovski (Georgia Tech) — Fenchel-type representations and large-scale problems with convex structure on difficult geometry domains · slides
  • Rodolphe Jenatton (Amazon) — Sparse and spurious: dictionary learning with noise and outliers · slides
  • Peter Richtárik (Edinburgh) — Stochastic dual Newton ascent for empirical risk minimization · slides
  • Martin Jaggi (ETH Zurich) — Frank-Wolfe optimization algorithms: a brief tutorial · slides
  • Katya Scheinberg (Lehigh) — Unconstrained trust region based stochastic optimization with biased and unbiased noise · slides
  • Robert Gower (Edinburgh) — Randomized iterative methods for linear systems and inverting matrices
  • Mark Schmidt (UBC) — Is greedy coordinate descent a terrible algorithm? · slides
  • Donald Goldfarb (Columbia) — Low-rank matrix and tensor recovery: theory and algorithms · slides
  • Zheng Qu (Edinburgh) — Randomized dual coordinate ascent with arbitrary sampling · slides
  • Jonathan Eckstein (Rutgers) — Object-parallel solution of large-scale lasso problems · slides
  • Patrick Louis Combettes (Paris 6) — Splitting techniques in the face of huge problem sizes · slides
  • François Glineur (Louvain) — Smooth strongly convex interpolation and exact worst-case performance of first-order methods · slides
  • Jakub Konečný (Edinburgh) — Distributed optimization with arbitrary local solvers · slides
  • Garud Iyengar (Columbia) — A distributed proximal method for composite convex optimization · slides

Program

6 May 2015 — Informatics Forum G.07

  • 09:40–10:15 Arkadi Nemirovski
  • 10:15–10:50 Rodolphe Jenatton
  • 11:20–11:55 Peter Richtárik
  • 11:55–12:45 Spotlight session 1
  • 12:45–14:15 Lunch and poster session 1
  • 14:15–14:50 Martin Jaggi
  • 14:50–15:25 Katya Scheinberg
  • 15:55–16:30 Robert Gower
  • 16:30–17:05 Mark Schmidt

7 May 2015 — Informatics Forum G.07

  • 09:40–10:15 Donald Goldfarb
  • 10:15–10:50 Zheng Qu
  • 11:20–11:55 Jonathan Eckstein
  • 11:55–12:45 Spotlight session 2
  • 12:45–14:15 Lunch and poster session 2
  • 14:15–14:50 Patrick Louis Combettes
  • 14:50–15:25 François Glineur
  • 15:55–16:30 Jakub Konečný
  • 16:30–17:05 Garud Iyengar

8 May 2015 — trek (morning) and colloquium, JCMB Lecture Theatre C

  • 09:30–12:30 Light trek to Arthur’s Seat
  • 14:00–15:00 Arkadi Nemirovski, On statistical inference via convex optimization
  • 15:00–15:10 Best poster award

Series: 2012 · 2013 · 2015 · 2018