algorithms   76162

« earlier    

[1808.00023] The Measure and Mismeasure of Fairness: A Critical Review of Fair Machine Learning
The nascent field of fair machine learning aims to ensure that decisions guided by algorithms are equitable. Over the last several years, three formal definitions of fairness have gained prominence: (1) anti-classification, meaning that protected attributes---like race, gender, and their proxies---are not explicitly used to make decisions; (2) classification parity, meaning that common measures of predictive performance (e.g., false positive and false negative rates) are equal across groups defined by the protected attributes; and (3) calibration, meaning that conditional on risk estimates, outcomes are independent of protected attributes. Here we show that all three of these fairness definitions suffer from significant statistical limitations. Requiring anti-classification or classification parity can, perversely, harm the very groups they were designed to protect; and calibration, though generally desirable, provides little guarantee that decisions are equitable. In contrast to these formal fairness criteria, we argue that it is often preferable to treat similarly risky people similarly, based on the most statistically accurate estimates of risk that one can produce. Such a strategy, while not universally applicable, often aligns well with policy objectives; notably, this strategy will typically violate both anti-classification and classification parity. In practice, it requires significant effort to construct suitable risk estimates. One must carefully define and measure the targets of prediction to avoid retrenching biases in the data. But, importantly, one cannot generally address these difficulties by requiring that algorithms satisfy popular mathematical formalizations of fairness. By highlighting these challenges in the foundation of fair machine learning, we hope to help researchers and practitioners productively advance the area.
machine_learning  algorithms  bias  ethics  privacy  review  for_friends 
2 days ago by rvenkat
Introduction to A*
Good explanation of the A* pathfinding algorithm.
algorithms  gamedev 
2 days ago by dmdavis
Introduction to A*
Interactive tutorial for A*, Dijkstra's Algorithm, and other pathfinding algorithms
algorithms  programming  graphs 
2 days ago by garrettc
Learning… by Alexander S. Kulikov et al. [PDF/iPad/Kindle]
Learning Algorithms Through Programming and Puzzle Solving
algorithms 
2 days ago by hellsten
javascript-algorithms
This repository contains JavaScript based examples of many popular algorithms and data structures.
cs  javascript  algorithms  datastructures 
3 days ago by gohai

« earlier    

related tags

(popular  3d  a*  advertising  ai  algo  algorithm  algorithms/data-structures/design-patterns  analysis  anomaly-detection  arms_race  art  artifical_intelligence  astar  automation  bellman-ford  bias  big-o  bigo  bigtech  book  bookmarks_bar  books  cheatsheet  chess  circle  coding  collaboration  complexity  compsci  computational_complexity  computer-science  computerscience  consensus  crdt  cs  data-structures  data  datascience  datastructures  dataviz  deep-learning  delta  design  dev  diff  diffing  diffs  digital_ethics  dijkstra  dimension  dimensions  directory  distance  distributed-systems  distributedsystems  drawing  ebook  editing  ericjang  ethics  evolutionary  exercises  facebook  fairness  fakenews  fibonacci  finance  finger-trees  for_friends  forecast  free  gamedev  generator  genetic  geometry  gis  goldman_sachs  google  graph-theory  graph  graph_theory  graphics-rendering  graphics  graphs  greedy  hash  haskell  healthcare  hii  history  ifttt  images  information-retrieval  interactiondesign  interesting  intro  javascript  js  keras  learning  lists  machine_learning  math  maze  memory  metric_spaces  ml  n  near  opensource  optimization  pathfinding  physics  pocket  points  politics  privacy  programming  psychology  python  quanta_mag  raft  reference  rendering  repository  review  ruby  rust  science  segmentfault  separation  sharelab  shortest-path  social  sociology  sorting  space  spaced_repetition  spatial  square  statistics  surveillanceoverride  tech  technology  testing  textbook  textdiff  timeseries  todo  toread  traders  tutorial  tutorials  ux  visualization  voxel  wall_street  weighted  winding  zookeeper 

Copy this bookmark:



description:


tags: