Share This Author
Stochastic Evolutionary Game Dynamics
The risk inflation criterion for multiple regression
A new criterion is proposed for the evaluation of variable selection procedures in multiple regression. This criterion, which we call the risk inflation, is based on an adjustment to the risk.…
A Spectral Algorithm for Latent Dirichlet Allocation
- Anima Anandkumar, Dean P. Foster, Daniel J. Hsu, S. Kakade, Yi-Kai Liu
- Computer ScienceAlgorithmica
- 30 April 2012
This work provides a simple and efficient learning procedure that is guaranteed to recover the parameters for a wide class of multi-view models and topic models, including latent Dirichlet allocation (LDA).
Calibration and empirical Bayes variable selection
For the problem of variable selection for the normal linear model, selection criteria such as AIC, C p , BIC and RIC have fixed dimensionality penalties. Such criteria are shown to correspond to…
An Operational Measure of Riskiness
We propose a measure of riskiness of “gambles” (risky assets) that is objective: it depends only on the gamble and not on the decision maker. The measure is based on identifying for every gamble the…
Continuous Record Asymptotics for Rolling Sample Variance Estimators
It is widely known that conditional covariances of asset returns change over time. Researchers adopt many strategies to accommodate conditional heteroskedasticity. Among the most popular are: (a)…
α‐investing: a procedure for sequential control of expected false discoveries
Summary. α‐investing is an adaptive sequential methodology that encompasses a large family of procedures for testing multiple hypotheses. All control mFDR, which is the ratio of the expected number…
Calibrated Learning and Correlated Equilibrium
For each correlated equilibrium there is some calibrated learning rule that the players can use which results in their playing this correlated equilibrium in the limit, and the statistical concept of a calibration is strongly related to the game theoretic concept of correlated equilibrium.
Stochastic Convex Optimization with Bandit Feedback
- Alekh Agarwal, Dean P. Foster, Daniel J. Hsu, S. Kakade, A. Rakhlin
- Computer Science, MathematicsSIAM J. Optim.
- 8 July 2011
This paper addresses the problem of minimizing a convex, Lipschitz function f over a conveX, compact set χ under a stochastic bandit feedback model and demonstrates a generalization of the ellipsoid algorithm that incurs O(poly (d) √T) regret.
PACT: Privacy-Sensitive Protocols And Mechanisms for Mobile Contact Tracing
This work advocates for a third-party free approach to assisted mobile contact tracing, because such an approach mitigates the security and privacy risks of requiring a trusted third party.