machine_learning   13746

« 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 
yesterday by rvenkat
tensor2tensor/tensor2tensor/mesh_tensorflow at master · tensorflow/tensor2tensor
Mesh TensorFlow (mtf) is a language for distributed deep learning, capable of specifying a broad class of distributed tensor computations. The purpose of mesh-tensorflow is to formalize and implement distribution strategies for your computation graph over your hardware/processors For example: "Split the batch over rows of processors and split the units in the hidden layer across columns of processors." Mesh-TensorFlow is implemented as a layer over TensorFlow.
TensorFlow  machine_learning 
3 days ago by amy

« earlier    

related tags

#fail  100days  acadêmico  ai  alexa  algorithms  analyze  anomaly_detect  anonymity  apple  architecture  art  autoencoders  autonomous_vehicles  basics  bayesian  bias  big_data  blockchain  cheatsheet  classification  cmle  code  coding  convolutional  cpus  curiosity  customer_service  data_science  data_visualization  datascience  decomposition  deep_learning  development  digital_ethics  distributed  econometrics  education  embeddings  energy  ethics  example  facebook  fairness  financial_services  for_friends  frontend  futurism  games_on  gan  gcp  generative  google  google_home  gpu  ground_truth  grupos  guide  harvard  howto  image  image_recognition  image_similarity  intrinsic  intrinsic_decomposition  intro  iot  javascript  julia  keras  language  law  lda  learning  lernen  lernherausforderung  logistics  lstms  machine_learning_101  machine_learning_cheatsheet  machinelearning  manufacturing  math  matrix_factorization  mit  ml  mobile  monkeylearn  natural_language_processing  netart  neural_nets  neural_networks  nlp  open_source  opensource  paper  payg  podcast  pokemon  principais  privacy  probability  programming  projects  python  python3  raspberry_pi  recommendations  regression  research  resources  review  rnns  robotics  rss  sap  scikit-learn  se4all  self_driving_cars  self_driving_vehicles  snips  social_science_methodology  sociology  solar  statistics  supply_chains  tensorflow  tesla  text-classification  text_analysis  to:nb  to_be_shot_after_a_fair_trial  to_read  toptoptop  tracking  translate  translation  trusted_computing  tutorial  urban_planning  video  voice_assistant  watson  wikipedia  word2vec 

Copy this bookmark: