Brian Ziebart on "Supervised Machine Learning as an Adversarial Game", March 31, 13:45, AA6214
Hi all,
the next tea-talk will be given by Prof. Brian Ziebart from the University of Illinois at Chicago. The talk will be held at 13:45 & AA6214. If you would like to chat with Brian, please fill your names and available time-slots on the below spreadsheet: https://docs.google.com/spreadsheets/d/14PpRI2WYl_zPlLPGC5SPQu4fFbJDFHIIXt4o...
Title: Supervised Machine Learning as an Adversarial Game
Abstract: A standard approach to supervised machine learning is to choose the form of a predictor and to then optimize its parameters based on training data. Approximations of the predictor's performance measure are often required to make this optimization problem tractable. Instead of approximating the performance measure and using the exact training data, this talk explores adversarial approximations of the training data while optimizing the exact performance measure. This formulation ensures stronger theoretical guarantees (e.g., Fisher consistency) than other surrogate loss methods, better aligns predictor construction with univariate and multivariate performance measures found in computer vision, information retrieval, and rank learning tasks, and provides flexibility for addressing sample selection bias for improved active learning.
Bio: Brian Ziebart is an Assistant Professor in the Department of Computer Science at the University of Illinois at Chicago. He earned his PhD in Machine Learning from Carnegie Mellon University where he was also a postdoctoral fellow. His interests lie in the intersections between machine learning, game theory, and decision theory. He has published over 25 articles in leading machine learning and artificial intelligence venues, including one that received a Best Paper award at the International Conference on Machine Learning.
Best, --Junyoung
Afficher les réponses par date
Hi all, if you are interested in talking with Prof. Brian Ziebart about research, please fill in a time-slot in this spreadsheet: https://docs.google.com/spreadsheets/d/14PpRI2WYl_ zPlLPGC5SPQu4fFbJDFHIIXt4oaqFdROc/edit?usp=sharing
--Junyoung
On Sun, Mar 26, 2017 at 10:00 PM, Junyoung Chung elecegg@gmail.com wrote:
Hi all,
the next tea-talk will be given by Prof. Brian Ziebart from the University of Illinois at Chicago. The talk will be held at 13:45 & AA6214. If you would like to chat with Brian, please fill your names and available time-slots on the below spreadsheet: https://docs.google.com/spreadsheets/d/14PpRI2WYl_ zPlLPGC5SPQu4fFbJDFHIIXt4oaqFdROc/edit?usp=sharing
Title: Supervised Machine Learning as an Adversarial Game
Abstract: A standard approach to supervised machine learning is to choose the form of a predictor and to then optimize its parameters based on training data. Approximations of the predictor's performance measure are often required to make this optimization problem tractable. Instead of approximating the performance measure and using the exact training data, this talk explores adversarial approximations of the training data while optimizing the exact performance measure. This formulation ensures stronger theoretical guarantees (e.g., Fisher consistency) than other surrogate loss methods, better aligns predictor construction with univariate and multivariate performance measures found in computer vision, information retrieval, and rank learning tasks, and provides flexibility for addressing sample selection bias for improved active learning.
Bio: Brian Ziebart is an Assistant Professor in the Department of Computer Science at the University of Illinois at Chicago. He earned his PhD in Machine Learning from Carnegie Mellon University where he was also a postdoctoral fellow. His interests lie in the intersections between machine learning, game theory, and decision theory. He has published over 25 articles in leading machine learning and artificial intelligence venues, including one that received a Best Paper award at the International Conference on Machine Learning.
Best, --Junyoung
I think it would be useful for anyone who is interested in *covariate shift, robustness, or adversarial examples* to speak with him!
On Wed, Mar 29, 2017 at 5:10 PM, Junyoung Chung elecegg@gmail.com wrote:
Hi all, if you are interested in talking with Prof. Brian Ziebart about research, please fill in a time-slot in this spreadsheet: https://docs.google.com/spreadsheets/d/14PpRI2WYl_zPlLPGC5SP Qu4fFbJDFHIIXt4oaqFdROc/edit?usp=sharing
--Junyoung
On Sun, Mar 26, 2017 at 10:00 PM, Junyoung Chung elecegg@gmail.com wrote:
Hi all,
the next tea-talk will be given by Prof. Brian Ziebart from the University of Illinois at Chicago. The talk will be held at 13:45 & AA6214. If you would like to chat with Brian, please fill your names and available time-slots on the below spreadsheet: https://docs.google.com/spreadsheets/d/14PpRI2WYl_zPlLPGC5SP Qu4fFbJDFHIIXt4oaqFdROc/edit?usp=sharing
Title: Supervised Machine Learning as an Adversarial Game
Abstract: A standard approach to supervised machine learning is to choose the form of a predictor and to then optimize its parameters based on training data. Approximations of the predictor's performance measure are often required to make this optimization problem tractable. Instead of approximating the performance measure and using the exact training data, this talk explores adversarial approximations of the training data while optimizing the exact performance measure. This formulation ensures stronger theoretical guarantees (e.g., Fisher consistency) than other surrogate loss methods, better aligns predictor construction with univariate and multivariate performance measures found in computer vision, information retrieval, and rank learning tasks, and provides flexibility for addressing sample selection bias for improved active learning.
Bio: Brian Ziebart is an Assistant Professor in the Department of Computer Science at the University of Illinois at Chicago. He earned his PhD in Machine Learning from Carnegie Mellon University where he was also a postdoctoral fellow. His interests lie in the intersections between machine learning, game theory, and decision theory. He has published over 25 articles in leading machine learning and artificial intelligence venues, including one that received a Best Paper award at the International Conference on Machine Learning.
Best, --Junyoung
Lisa_labo mailing list Lisa_labo@iro.umontreal.ca https://webmail.iro.umontreal.ca/mailman/listinfo/lisa_labo
Any chance Brian can share his slides for people who won't be able to attend?
On Wed, Mar 29, 2017 at 5:18 PM David Krueger david.scott.krueger@gmail.com wrote:
I think it would be useful for anyone who is interested in *covariate shift, robustness, or adversarial examples* to speak with him!
On Wed, Mar 29, 2017 at 5:10 PM, Junyoung Chung elecegg@gmail.com wrote:
Hi all, if you are interested in talking with Prof. Brian Ziebart about research, please fill in a time-slot in this spreadsheet:
https://docs.google.com/spreadsheets/d/14PpRI2WYl_zPlLPGC5SPQu4fFbJDFHIIXt4o...
--Junyoung
On Sun, Mar 26, 2017 at 10:00 PM, Junyoung Chung elecegg@gmail.com wrote:
Hi all,
the next tea-talk will be given by Prof. Brian Ziebart from the University of Illinois at Chicago. The talk will be held at 13:45 & AA6214. If you would like to chat with Brian, please fill your names and available time-slots on the below spreadsheet:
https://docs.google.com/spreadsheets/d/14PpRI2WYl_zPlLPGC5SPQu4fFbJDFHIIXt4o...
Title: Supervised Machine Learning as an Adversarial Game
Abstract: A standard approach to supervised machine learning is to choose the form of a predictor and to then optimize its parameters based on training data. Approximations of the predictor's performance measure are often required to make this optimization problem tractable. Instead of approximating the performance measure and using the exact training data, this talk explores adversarial approximations of the training data while optimizing the exact performance measure. This formulation ensures stronger theoretical guarantees (e.g., Fisher consistency) than other surrogate loss methods, better aligns predictor construction with univariate and multivariate performance measures found in computer vision, information retrieval, and rank learning tasks, and provides flexibility for addressing sample selection bias for improved active learning.
Bio: Brian Ziebart is an Assistant Professor in the Department of Computer Science at the University of Illinois at Chicago. He earned his PhD in Machine Learning from Carnegie Mellon University where he was also a postdoctoral fellow. His interests lie in the intersections between machine learning, game theory, and decision theory. He has published over 25 articles in leading machine learning and artificial intelligence venues, including one that received a Best Paper award at the International Conference on Machine Learning.
Best, --Junyoung
Lisa_labo mailing list Lisa_labo@iro.umontreal.ca https://webmail.iro.umontreal.ca/mailman/listinfo/lisa_labo
Lisa_seminaires mailing list Lisa_seminaires@iro.umontreal.ca https://webmail.iro.umontreal.ca/mailman/listinfo/lisa_seminaires
Hi all,
the room is changed to AA5340.
Best,
On Sun, Mar 26, 2017 at 10:00 PM Junyoung Chung elecegg@gmail.com wrote:
Hi all,
the next tea-talk will be given by Prof. Brian Ziebart from the University of Illinois at Chicago. The talk will be held at 13:45 & AA6214. If you would like to chat with Brian, please fill your names and available time-slots on the below spreadsheet: https://docs.google.com/spreadsheets/d/14PpRI2WYl_zPlLPGC5SPQu4fFbJDFHIIXt4o...
Title: Supervised Machine Learning as an Adversarial Game
Abstract: A standard approach to supervised machine learning is to choose the form of a predictor and to then optimize its parameters based on training data. Approximations of the predictor's performance measure are often required to make this optimization problem tractable. Instead of approximating the performance measure and using the exact training data, this talk explores adversarial approximations of the training data while optimizing the exact performance measure. This formulation ensures stronger theoretical guarantees (e.g., Fisher consistency) than other surrogate loss methods, better aligns predictor construction with univariate and multivariate performance measures found in computer vision, information retrieval, and rank learning tasks, and provides flexibility for addressing sample selection bias for improved active learning.
Bio: Brian Ziebart is an Assistant Professor in the Department of Computer Science at the University of Illinois at Chicago. He earned his PhD in Machine Learning from Carnegie Mellon University where he was also a postdoctoral fellow. His interests lie in the intersections between machine learning, game theory, and decision theory. He has published over 25 articles in leading machine learning and artificial intelligence venues, including one that received a Best Paper award at the International Conference on Machine Learning.
Best, --Junyoung
Hi all,
we have a talk today by Prof. Brian Ziebart.
The location has changed from AA6214 to AA5340. It will begin as usual at 13:45.
Best, -Junyoung
On Sun, Mar 26, 2017 at 10:00 PM Junyoung Chung elecegg@gmail.com wrote:
Hi all,
the next tea-talk will be given by Prof. Brian Ziebart from the University of Illinois at Chicago. The talk will be held at 13:45 & AA6214. If you would like to chat with Brian, please fill your names and available time-slots on the below spreadsheet:
https://docs.google.com/spreadsheets/d/14PpRI2WYl_zPlLPGC5SPQu4fFbJDFHIIXt4o...
Title: Supervised Machine Learning as an Adversarial Game
Abstract: A standard approach to supervised machine learning is to choose the form of a predictor and to then optimize its parameters based on training data. Approximations of the predictor's performance measure are often required to make this optimization problem tractable. Instead of approximating the performance measure and using the exact training data, this talk explores adversarial approximations of the training data while optimizing the exact performance measure. This formulation ensures stronger theoretical guarantees (e.g., Fisher consistency) than other surrogate loss methods, better aligns predictor construction with univariate and multivariate performance measures found in computer vision, information retrieval, and rank learning tasks, and provides flexibility for addressing sample selection bias for improved active learning.
Bio: Brian Ziebart is an Assistant Professor in the Department of Computer Science at the University of Illinois at Chicago. He earned his PhD in Machine Learning from Carnegie Mellon University where he was also a postdoctoral fellow. His interests lie in the intersections between machine learning, game theory, and decision theory. He has published over 25 articles in leading machine learning and artificial intelligence venues, including one that received a Best Paper award at the International Conference on Machine Learning.
Best, --Junyoung
The talk will be in 30 minutes! The room is AA5340.
On Fri, Mar 31, 2017 at 8:33 AM Junyoung Chung elecegg@gmail.com wrote:
Hi all,
we have a talk today by Prof. Brian Ziebart.
The location has changed from AA6214 to AA5340. It will begin as usual at 13:45.
Best, -Junyoung
On Sun, Mar 26, 2017 at 10:00 PM Junyoung Chung elecegg@gmail.com wrote:
Hi all,
the next tea-talk will be given by Prof. Brian Ziebart from the University of Illinois at Chicago. The talk will be held at 13:45 & AA6214. If you would like to chat with Brian, please fill your names and available time-slots on the below spreadsheet:
https://docs.google.com/spreadsheets/d/14PpRI2WYl_zPlLPGC5SPQu4fFbJDFHIIXt4o...
Title: Supervised Machine Learning as an Adversarial Game
Abstract: A standard approach to supervised machine learning is to choose the form of a predictor and to then optimize its parameters based on training data. Approximations of the predictor's performance measure are often required to make this optimization problem tractable. Instead of approximating the performance measure and using the exact training data, this talk explores adversarial approximations of the training data while optimizing the exact performance measure. This formulation ensures stronger theoretical guarantees (e.g., Fisher consistency) than other surrogate loss methods, better aligns predictor construction with univariate and multivariate performance measures found in computer vision, information retrieval, and rank learning tasks, and provides flexibility for addressing sample selection bias for improved active learning.
Bio: Brian Ziebart is an Assistant Professor in the Department of Computer Science at the University of Illinois at Chicago. He earned his PhD in Machine Learning from Carnegie Mellon University where he was also a postdoctoral fellow. His interests lie in the intersections between machine learning, game theory, and decision theory. He has published over 25 articles in leading machine learning and artificial intelligence venues, including one that received a Best Paper award at the International Conference on Machine Learning.
Best, --Junyoung
-- --Junyoung
lisa_seminaires@iro.umontreal.ca
-
David Krueger -
Junyoung Chung -
Vincent Dumoulin