Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
- Tolga Bolukbasi, Kai-Wei Chang, James Y. Zou, Venkatesh Saligrama, A. Kalai
- Computer ScienceNIPS
- 21 July 2016
This work empirically demonstrates that its algorithms significantly reduce gender bias in embeddings while preserving the its useful properties such as the ability to cluster related concepts and to solve analogy tasks.
Online convex optimization in the bandit setting: gradient descent without a gradient
- A. Flaxman, A. Kalai, H. B. McMahan
- Computer ScienceACM-SIAM Symposium on Discrete Algorithms
- 2 August 2004
It is possible to use gradient descent without seeing anything more than the value of the functions at a single point, and the guarantees hold even in the most general case: online against an adaptive adversary.
Efficient algorithms for online decision problems
Noise-tolerant learning, the parity problem, and the statistical query model
The algorithm runs in polynomial time for the case of parity functions that depend on only the first O(log n log log n) bits of input, which provides the first known instance of an efficient noise-tolerant algorithm for a concept class that is not learnable in the Statistical Query model of Kearns .
Adaptively Learning the Crowd Kernel
- O. Tamuz, Ce Liu, Serge J. Belongie, O. Shamir, A. Kalai
- Computer ScienceInternational Conference on Machine Learning
- 5 May 2011
An algorithm that, given n objects, learns a similarity matrix over all n2 pairs, from crowdsourced data alone is introduced, and SVMs reveal that the crowd kernel captures prominent and subtle features across a number of domains.
Agnostically learning halfspaces
- A. Kalai, Adam R. Klivans, Y. Mansour, R. Servedio
- Computer ScienceIEEE Annual Symposium on Foundations of Computer…
- 23 October 2005
We give the first algorithm that (under distributional assumptions) efficiently learns halfspaces in the notoriously difficult agnostic framework of Kearns, Schapire, & Sellie, where a learner is…
Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting
A large-scale study of gender bias in occupation classification, a task where the use of machine learning may lead to negative outcomes on peoples' lives, and the impact on occupation classification of including explicit gender indicators in different semantic representations of online biographies.
Universal Portfolios With and Without Transaction Costs
This work provides a simple analysis which naturally extends to the case of a fixed percentage transaction cost (commission) and presents a simple randomized implementation that is significantly faster in practice.
Analysis of Perceptron-Based Active Learning
- S. Dasgupta, A. Kalai, C. Monteleoni
- Computer ScienceAnnual Conference Computational Learning Theory
- 1 December 2009
A simple selective sampling algorithm is presented, which combines a modification of the perceptron update with an adaptive filtering rule for deciding which points to query and reaches generalization error e after asking for just O(d log 1/∈) labels.
Efficient algorithms for universal portfolios
- A. Kalai, S. Vempala
- Computer ScienceProceedings 41st Annual Symposium on Foundations…
- 12 November 2000
This work presents an efficient implementation of the Universal algorithm that is based on non-uniform random walks that are rapidly mixing that works for non-financial applications of theUniversal algorithm, such as data compression and language modeling.