Zobrazeno 1 - 10
of 94
pro vyhledávání: '"Rothblum, Guy N."'
Autor:
Asi, Hilal, Boemer, Fabian, Genise, Nicholas, Mughees, Muhammad Haris, Ogilvie, Tabitha, Rishi, Rehan, Rothblum, Guy N., Talwar, Kunal, Tarbe, Karl, Zhu, Ruiyu, Zuliani, Marco
This paper presents Wally, a private search system that supports efficient semantic and keyword search queries against large databases. When sufficient clients are making the queries, Wally performance is significantly better than previous systems. I
Externí odkaz:
http://arxiv.org/abs/2406.06761
Consider a multi-class labelling problem, where the labels can take values in $[k]$, and a predictor predicts a distribution over the labels. In this work, we study the following foundational question: Are there notions of multi-class calibration tha
Externí odkaz:
http://arxiv.org/abs/2402.07821
Secure aggregation of high-dimensional vectors is a fundamental primitive in federated statistics and learning. A two-server system such as PRIO allows for scalable aggregation of secret-shared vectors. Adversarial clients might try to manipulate the
Externí odkaz:
http://arxiv.org/abs/2311.10237
Autor:
Rothblum, Guy N., Yona, Gal
ML-based predictions are used to inform consequential decisions about individuals. How should we use predictions (e.g., risk of heart attack) to inform downstream binary classification decisions (e.g., undergoing a medical procedure)? When the risk e
Externí odkaz:
http://arxiv.org/abs/2203.09852
There are growing concerns that algorithms, which increasingly make or influence important decisions pertaining to individuals, might produce outcomes that discriminate against protected groups. We study such fairness concerns in the context of a two
Externí odkaz:
http://arxiv.org/abs/2111.10885
Autor:
Rothblum, Guy N., Yona, Gal
In many machine learning settings there is an inherent tension between fairness and accuracy desiderata. How should one proceed in light of such trade-offs? In this work we introduce and study $\gamma$-disqualification, a new framework for reasoning
Externí odkaz:
http://arxiv.org/abs/2110.00813
Autor:
Rothblum, Guy N, Yona, Gal
An agnostic PAC learning algorithm finds a predictor that is competitive with the best predictor in a benchmark hypothesis class, where competitiveness is measured with respect to a given loss function. However, its predictions might be quite sub-opt
Externí odkaz:
http://arxiv.org/abs/2105.09989
Prediction algorithms assign numbers to individuals that are popularly understood as individual "probabilities" -- what is the probability of 5-year survival after cancer diagnosis? -- and which increasingly form the basis for life-altering decisions
Externí odkaz:
http://arxiv.org/abs/2011.13426
It is well understood that classification algorithms, for example, for deciding on loan applications, cannot be evaluated for fairness without taking context into account. We examine what can be learned from a fairness oracle equipped with an underly
Externí odkaz:
http://arxiv.org/abs/2004.01840
Autor:
Aaronson, Scott, Rothblum, Guy N.
In differential privacy (DP), we want to query a database about n users, in a way that "leaks at most eps about any individual user," even conditioned on any outcome of the query. Meanwhile, in gentle measurement, we want to measure n quantum states,
Externí odkaz:
http://arxiv.org/abs/1904.08747