Improved Regret Guarantees for Online Smooth Convex Optimization with Bandit Feedback Ankan Saha University of Chicago

First Page		Document Content
Date: 2011-04-04 16:05:29 Convex analysis Operations research Convex optimization Convex function Interior point method Lipschitz continuity Linear programming Self-concordant function Gradient descent Mathematical optimization Numerical analysis Mathematical analysis		Improved Regret Guarantees for Online Smooth Convex Optimization with Bandit Feedback Ankan Saha University of Chicago Add to Reading List Source URL: people.cs.uchicago.edu Download Document from Source Website File Size: 318,88 KB Share Document on Facebook

	Hybrid Approximate Gradient and Stochastic Descent for Falsification of Nonlinear Systems Shakiba Yaghoubi and Georgios Fainekos Abstract— Studying transient properties of nonlinear systems is an important problem for DocID: 1xUAR - View Document
	Understanding and Optimizing Asynchronous Low-Precision Stochastic Gradient Descent Christopher De Sa Matthew Feldman Christopher Ré Kunle Olukotun Departments of Electrical Engineering and Computer Science Stanford Uni DocID: 1vj6v - View Document
	Distributed Gradient Descent in Bacterial Food Search Shashank Singh∗1 , Sabrina Rashid∗2 , Saket Navlakha3 , Ziv Bar-Joseph4† 1 Machine Learning Department and Department of Statistics, Carnegie Mellon University, DocID: 1vhcx - View Document
	Stat 928: Statistical Learning Theory Lecture: 22 Exponentiated Gradient Descent Instructor: Sham Kakade DocID: 1vbLp - View Document
	Pattern Recognition And Machine Learning - EPFL - Fall 2015 Emtiyaz Khan, Timur Bagautdinov, Carlos Becker, Ilija Bogunovic & Ksenia Konyushkova 2. Linear Regression and Gradient Descent 2.1 DocID: 1v534 - View Document