Machine Learning for Algorithms (ML4A)

Summer '21


While algorithms in computer science and optimization have classically supported machine learning, in recent years there has been increasing interest in the reverse direction: using machine learning to improve the performance of classical algorithms in computer science, by fine-tuning their behavior to adapt to the properties of the input distribution. Many applications involve processing streams of data (video, data logs, customer activity etc) by executing the same algorithm on an hourly, daily or weekly basis. These data sets are typically not "random" or "worst-case"; instead, they come from some distribution which does not change rapidly from execution to execution. This makes it possible to design better algorithms tailored to the specific data distribution, trained on past instances of the problem. This "data-driven" or "learning-based" approach to algorithm design has the potential to significantly improve the efficiency of some of the most widely used algorithms. For example, they have been used to design better data structures, online algorithms, streaming and sketching algorithms, market mechanisms and algorithms for combinatorial optimization, similarity search and inverse problems. This workshop will feature talks from experts at the forefront of this exciting area.


The workshop will take place virtually on July 13-14, 2021. Links for virtual participation will be shared to registrants in advance of the workshop.

Confirmed speakers

  • Alex Dimakis (UT Austin)
  • Yonina Eldar (Weizmann)
  • Anna Goldie (Google Brain, Stanford)
  • Reinhard Heckel (Technical University of Munich)
  • Stefanie Jegelka (MIT)
  • Tim Kraska (MIT)
  • Benjamin Moseley (CMU)
  • David Parkes (Harvard)
  • Ola Svensson (EPFL)
  • Tuomas Sandholm (CMU, Optimized Markets, Strategy Robot, Strategic Machine)
  • Sergei Vassilvitski (Google)
  • Ellen Vitercik (CMU/UC Berkeley)
  • David Woodruff (CMU)


  • Costis Daskalakis (MIT)
  • Paul Hand (Northeastern)
  • Piotr Indyk (MIT)
  • Michael Mitzenmacher (Harvard)
  • Ronitt Rubinfeld (MIT)
  • Jelani Nelson (UC Berkeley)


Day 1: Tuesday, July 13, 2021

Time Speaker Title

Day 2: Wednesday, July 14, 2021

Time Speaker Title
function autoCenter() { // Create a new viewpoint bound var bounds = new google.maps.LatLngBounds(); // Go through each... for (var i = 0; i < markers.length; i++) { bounds.extend(markers[i].position); } // Fit these bounds to the map map.fitBounds(bounds); }