PPT-How Robust are Linear Sketches to Adaptive Inputs?

Author : sherrill-nordquist | Published Date : 2015-11-22

Moritz Hardt David P Woodruff IBM Research Almaden Two Aspects of Coping with Big Data Efficiency Handle enormous inputs Robustness Handle adverse conditions

Presentation Embed Code

Download Presentation

Download Presentation The PPT/PDF document "How Robust are Linear Sketches to Adapti..." is the property of its rightful owner. Permission is granted to download and print the materials on this website for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.

How Robust are Linear Sketches to Adaptive Inputs?: Transcript

Moritz Hardt David P Woodruff IBM Research Almaden Two Aspects of Coping with Big Data Efficiency Handle enormous inputs Robustness Handle adverse conditions Big Question Can we have both. 3 p 23932397 Issue Date 1999 URL httphdlhandlenet1072246117 Rights 1999 IEEE Personal use of this material is permitted However permission to reprintrepublish this material for advertising or promotional purposes or for creating new collective works Alexandr. . Andoni. . (Simons Institute). Robert . Krauthgamer. . (. Weizmann. . Institute). Ilya Razenshteyn . (CSAIL MIT). 1. Sketching. Compress a massive object to a . small. . sketch. Rich theories: . are Equivalent for Norms. Alexandr Andoni . (Simons Inst. / Columbia). Robert . Krauthgamer. . (Weizmann. . Inst.). Ilya . Razenshteyn . (MIT, now at IBM . Almaden. ). 1. Sketching. n. d. When is sketching possible?. Statistics for High-Dimensional Data (. Buhlmann. & van de Geer). Lasso. Proposed by . Tibshirani. (1996). Least Absolute Shrinkage and Selection Operator. Why we still use it. Accurate in prediction and variable selection (under certain assumptions) and computationally feasible. General Tools for Post-Selection Inference. Aaron Roth. What do we want to protect against?. Over-fitting from fixed algorithmic procedures (easiest – might hope to analyze exactly). e.g. variable/parameter selection followed by model fitting. Definition. Consequences of heteroscedasticity. Testing for . Heteroskedasticity. Breusch-Pagan. White test (2 forms). Fixing the problem. Robust standard errors. Weighted Least Squares. Fixing heteroskedasticity in LPM model.. General Tools for Post-Selection Inference. Aaron Roth. From: . Trustworthy-broker@trustme.com. To: . aaroth@cis.upenn.edu. Date: 2/27/15. Subject: Gr8 investment tip!!!. Hi! You don’t know me, but here is a tip! . Moritz . Hardt. , David P. Woodruff. IBM Research . Almaden. Two Aspects of Coping with Big Data. Efficiency. Handle. enormous inputs. Robustness. Handle . adverse conditions. Big Question: Can we have both?. What are “Stochastic, Robust, and Adaptive” Controllers?. Stochastic Optimal. Control. Deterministic . versus. Stochastic . Optimization. Linear-Quadratic Gaussian (LQG). Optimal Control Law. Linear-Quadratic-Gaussian Control of a Dynamic Process. https://www.google.com/. search?hl. =. en&site. =. imghp&tbm. =. isch&source. =. hp&biw. =1280&bih=887&q=. davinci sketches&oq. =. davinci sketches&gs_l. =img.3..0i10l8j0i5i10.1328.4173.0.4309.16.16.0.0.0.0.87.1097.16.16.0....0...1ac.1.52.img..0.16.1088.veaqsSj_8dY#facrc=_&. 2D Sketches. 1. 2D Sketches. Profiles:. Closed loop shape that is drawn on a flat 2D plane (referred to as a datum) and is used to create 3D objects.. 2D Profiles consist of:. Points. Lines. Circles. WLS solution. (Weighted LS) . robust weights require . a nonlinear inversion such as IRLS.. . . IRLS (Iteratively Reweighted LS). (2.1)Technical Efficiency refers to the ability to:1. Produce the maximum amount of outputs for a specific quantity of inputs (outputincreasing notion), and/or2. Use the minimum amount of inputs to pr Michael Albert and Vincent Conitzer. malbert@cs.duke.edu. and . conitzer@cs.duke.edu. . Prior-Dependent Mechanisms. In many situations we’ve seen, optimal mechanisms are prior dependent. Myerson auction for independent bidder valuations.

Download Document

Here is the link to download the presentation.
"How Robust are Linear Sketches to Adaptive Inputs?"The content belongs to its owner. You may download and print it for personal use, without modification, and keep all copyright notices. By downloading, you agree to these terms.