A
Adam Tauman Kalai
Researcher at Microsoft
Publications - 158
Citations - 11369
Adam Tauman Kalai is an academic researcher from Microsoft. The author has contributed to research in topics: Computer science & Convex optimization. The author has an hindex of 47, co-authored 147 publications receiving 9526 citations. Previous affiliations of Adam Tauman Kalai include Northwestern University & Toyota.
Papers
More filters
Proceedings Article
Compression without a common prior: An information-theoretic justification for ambiguity in language
TL;DR: This work model this information-theoretically using the following question: what type of compression scheme would be efiective when the encoder and decoder have (boundedly) difierent prior probability distributions and uses information theory to justify why ambiguity is necessary for the purpose of compression.
Proceedings ArticleDOI
Static optimality and dynamic search-optimality in lists and trees
TL;DR: This paper shows that for the case of lists, one can achieve a 1 + e ratio with respect to the best static list in hindsight, by a simple efficient algorithm, and shows a (computationally inefficient) algorithm that achieves "dynamic search optimality": dynamic optimality if the online algorithm to make free rotations after each request.
Posted Content
The Disparate Equilibria of Algorithmic Decision Making when Individuals Invest Rationally
Lydia T. Liu,Ashia C. Wilson,Nika Haghtalab,Adam Tauman Kalai,Christian Borgs,Jennifer Chayes +5 more
TL;DR: In this article, the authors study a dynamic learning setting where individuals invest in a positive outcome based on their group's expected gain and the decision rule is updated to maximize institutional benefit.
Proceedings Article
An Approach to Bounded Rationality
TL;DR: A simple model of a game with additional costs for each strategy is formed, proving a counter-intuitive generalization of the classic min-max theorem to zero-sum games with the addition of strategy costs and showing that potential games with strategy costs remain potential games.
Proceedings ArticleDOI
What’s in a Name? Reducing Bias in Bios without Access to Protected Attributes
Alexey Romanov,Maria De-Arteaga,Hanna Wallach,Jennifer Chayes,Christian Borgs,Alexandra Chouldechova,Sahin Cem Geyik,Krishnaram Kenthapadi,Anna Rumshisky,Adam Tauman Kalai +9 more
TL;DR: This work proposes a method for discouraging correlation between the predicted probability of an individual’s true occupation and a word embedding of their name, which leverages the societal biases that are encoded in word embeddings, eliminating the need for access to protected attributes.