Domain-Adversarial Neural Networks

Size: px
Start display at page:

Download "Domain-Adversarial Neural Networks"

Transcription

1 Domain-Adversarial Neural Networks Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario Marchand Département d informatique et de génie logiciel, Université Laval, Québec, Canada Département d informatique, Université de Sherbrooke, Québec, Canada Groupe de recherche en apprentissage automatique de l Université Laval (GRAAL) December, Pascal Germain (GRAAL) Domain-Adversarial Neural Networks December, /

2 Outline Domain Adaptation Setting Theoretical Foundations Neural Network for Domain Adaptation Empirical Results Pascal Germain (GRAAL) Domain-Adversarial Neural Networks December, /

3 Our Domain Adaptation Setting Binary classification tasks Input space: R d Labels: {, } Two different data distributions Source domain: D S Target domain: D T A domain adaptation learning algorithm is provided with a labeled source sample S = {(x s i, y s i )} m i= (D S ) m, an unlabeled target sample T = {x t i } m i= (D T ) m. The goal is to build a classifier η : R d {, } with a low target risk R DT (η) def = Pr (x t,y t ) D T [η(x t ) y t ]. Pascal Germain (GRAAL) Domain-Adversarial Neural Networks December, /

4 Divergence between source and target domains Definition (Ben David et al., 6) Given two domain distributions D S and D T, and a hypothesis class H, the H-divergence between D S and D T is def [ d H (D S, D T ) = sup Pr η(x s ) = ] [ Pr η(x t ) = ] η H x s D S x t D T. [ = sup Pr η(x s ) = ] [ + Pr η(x t ) = ] η H x s D S x t D T. The H-divergence measures the ability of an hypothesis class H to discriminate between source D S and target D T distributions. Pascal Germain (GRAAL) Domain-Adversarial Neural Networks December, /

5 Bound on the target risk Theorem (Ben David et al., 6) Let H be a hypothesis class of VC-dimension d. With probability δ over the choice of samples S (D S ) m and T (D T ) m, for every η H: R DT (η) R S (η)+ m with β inf η H [R D S (η )+R DT (η )]. Empirical risk on the source sample: d log e m d + log δ +ˆd H (S, T )+ m d log m d + log δ +β R S (η) Empirical H-divergence: [ ˆd H (S, T ) def = max η H m def = m I [η(x s i ) y s i ]. i= I [η(x s i ) = ] + m i= ] I [η(x t i ) = ]. Pascal Germain (GRAAL) Domain-Adversarial Neural Networks December, 5 / i=

6 Bound on the target risk Theorem (Ben David et al., 6) Let H be a hypothesis class of VC-dimension d. With probability δ over the choice of samples S (D S ) m and T (D T ) m, for every η H: R DT (η) R S (η)+ m with β inf η H [R D S (η )+R DT (η )]. d log e m d + log δ +ˆd H (S, T )+ m d log m d + log δ +β Target risk R DT (η) is low if, given S and T, R S (η) is small, i.e., η H is good on and ˆd H(S, T ) is small, i.e., all η H are bad on Pascal Germain (GRAAL) Domain-Adversarial Neural Networks December, 6 /

7 Standard Neural Network Let consider a neural network architecture with one hidden layer h(x) = sigm(b + Wx), and f(h(x)) = softmax(c + Vh(x)). min W,V,b,c [ m ( ) ] log y s i f(h(x s i )). i= } {{ } source loss Given a source sample S = {(x s i, y s i )}m i= (D S) m,. Pick a x s S. Update V towards f(h(x s )) = y s. Update W towards f(h(x s )) = y s f(h(x)) h(x)... h(x) j... x... x j... V x d h(x) n W The hidden layer learns a representation h( ) from which linear hypothesis f( ) can classify source examples. Pascal Germain (GRAAL) Domain-Adversarial Neural Networks December, 7 /

8 Domain-Adversarial Neural Network (DANN) Empirical H-divergence [ ˆd H (S, T ) def = max η H m I [η(x s i ) = ] + m i= ] I [η(x t i ) = ]. i= We estimate the H-divergence by a logistic regressor that model the probability that a given input (either x s or x t ) is from the source domain: o(h(x)) def = sigm(d + w h(x)). Given a representation output by the hidden layer h( ) : [ ) ˆd H (h(s), h(t ) max log ( o(h(x s i )) ) + log ( o(h(x t i )) ) ]. w,d m m i= i= Pascal Germain (GRAAL) Domain-Adversarial Neural Networks December, 8 /

9 Domain-Adversarial Neural Network (DANN) min W,V,b,c [ m log ( y s i f(h(x s i )) ) ( +λ max i= } {{ } source loss w,d m log ( o(h(x s i )) ) + log ( o(h(x t m i )) )) ], i= i= } {{ } adaptation regularizer where λ > weights the domain adaptation regularization term. Given a source sample S = {(x s i, y s i )}m i= (D S) m, and a target sample T = {(x t i )}m i= (D T ) m,. Pick a x s S and x t T. Update V towards f(h(x s )) = y s. Update W towards f(h(x s )) = y s. Update w towards o(h(x s )) = and o(h(x t )) = 5. Update W towards o(h(x s )) = and o(h(x t )) = f(h(x)) DANN finds a representation h( ) that are good on S; but unable to discriminate between S and T. V h(x)... h(x) j... x... x j... o(h(x)) w h(x) n x d W Pascal Germain (GRAAL) Domain-Adversarial Neural Networks December, 9 /

10 Toy Dataset Standard Neural Network (NN) f(h(x)) Trained to classify source Trained to classify domains V h(x)... h(x) j... h(x) n W x x j x d Domain-Adversarial Neural Networks (DANN) f(h(x)) o(h(x)) Classification output: f(h(x)) Domain output: o(h(x)) V w h(x)... h(x) j... h(x) n W x x j x d Pascal Germain (GRAAL) Domain-Adversarial Neural Networks December, /

11 Amazon Reviews Input: product review (bag of words) Output: positive or negative rating. Dataset DANN NN books dvd..99 books electronics.6.5 books kitchen..5 dvd books.7.6 dvd electronics.7.56 dvd kitchen.7.7 electronics books.8.8 electronics dvd.7.77 electronics kitchen.8.9 kitchen books.8.88 kitchen dvd.6.6 kitchen electronics.6.6 Note: We use a small labeled subset of target examples to select the hyperparameters. Pascal Germain (GRAAL) Domain-Adversarial Neural Networks December, /

12 Marginalized Stacked Denoising Autoencoders (msda) Question Does DANN can be combined with other representation learning techniques for domain adaptation? The autoencoders msda (Chen et al. ) provides a new common representation for source and target (unsupervised) With msda+svm, Chen et al. () obtained state-of-the-art results on Amazon Reviews: Train a linear SVM on msda source representations. We try msda+dann: Train DANN on source representations and target representations. Pascal Germain (GRAAL) Domain-Adversarial Neural Networks December, /

13 Amazon Reviews Input: product review (bag of words) Output: positive or negative rating. Dataset msda+dann msda+svm books dvd books electronics.97. books kitchen.69.7 dvd books dvd electronics.8. dvd kitchen.5.78 electronics books.7.9 electronics dvd.6.6 electronics kitchen.8.7 kitchen books.. kitchen dvd.8.9 kitchen electronics..8 Note: We use a small labeled subset of target examples to select the hyperparameters. The noise parameter of msda representations is fixed to 5%. Pascal Germain (GRAAL) Domain-Adversarial Neural Networks December, /

14 Future Work Several paths to explore: Deeper neural networks architectures. Multiclass / Multilabels problems. Multisource domain adaptation. Thank you! Pascal Germain (GRAAL) Domain-Adversarial Neural Networks December, /

Domain-Adversarial Neural Networks

Domain-Adversarial Neural Networks Doain-Adversarial Neural Networks Hana Ajakan, Pascal Gerain 2, Hugo Larochelle 3, François Laviolette 2, Mario Marchand 2,2 Départeent d inforatique et de génie logiciel, Université Laval, Québec, Canada

More information

PAC-Bayesian Learning and Domain Adaptation

PAC-Bayesian Learning and Domain Adaptation PAC-Bayesian Learning and Domain Adaptation Pascal Germain 1 François Laviolette 1 Amaury Habrard 2 Emilie Morvant 3 1 GRAAL Machine Learning Research Group Département d informatique et de génie logiciel

More information

Generalization of the PAC-Bayesian Theory

Generalization of the PAC-Bayesian Theory Generalization of the PACBayesian Theory and Applications to SemiSupervised Learning Pascal Germain INRIA Paris (SIERRA Team) Modal Seminar INRIA Lille January 24, 2017 Dans la vie, l essentiel est de

More information

A Pseudo-Boolean Set Covering Machine

A Pseudo-Boolean Set Covering Machine A Pseudo-Boolean Set Covering Machine Pascal Germain, Sébastien Giguère, Jean-Francis Roy, Brice Zirakiza, François Laviolette, and Claude-Guy Quimper GRAAL (Université Laval, Québec city) October 9, 2012

More information

A Pseudo-Boolean Set Covering Machine

A Pseudo-Boolean Set Covering Machine A Pseudo-Boolean Set Covering Machine Pascal Germain, Sébastien Giguère, Jean-Francis Roy, Brice Zirakiza, François Laviolette, and Claude-Guy Quimper Département d informatique et de génie logiciel, Université

More information

Few-shot learning with KRR

Few-shot learning with KRR Few-shot learning with KRR Prudencio Tossou Groupe de Recherche en Apprentissage Automatique Départment d informatique et de génie logiciel Université Laval April 6, 2018 Prudencio Tossou (UL) Few-shot

More information

ECE521 Lectures 9 Fully Connected Neural Networks

ECE521 Lectures 9 Fully Connected Neural Networks ECE521 Lectures 9 Fully Connected Neural Networks Outline Multi-class classification Learning multi-layer neural networks 2 Measuring distance in probability space We learnt that the squared L2 distance

More information

Learning Deep Architectures for AI. Part II - Vijay Chakilam

Learning Deep Architectures for AI. Part II - Vijay Chakilam Learning Deep Architectures for AI - Yoshua Bengio Part II - Vijay Chakilam Limitations of Perceptron x1 W, b 0,1 1,1 y x2 weight plane output =1 output =0 There is no value for W and b such that the model

More information

IFT Lecture 7 Elements of statistical learning theory

IFT Lecture 7 Elements of statistical learning theory IFT 6085 - Lecture 7 Elements of statistical learning theory This version of the notes has not yet been thoroughly checked. Please report any bugs to the scribes or instructor. Scribe(s): Brady Neal and

More information

Does Unlabeled Data Help?

Does Unlabeled Data Help? Does Unlabeled Data Help? Worst-case Analysis of the Sample Complexity of Semi-supervised Learning. Ben-David, Lu and Pal; COLT, 2008. Presentation by Ashish Rastogi Courant Machine Learning Seminar. Outline

More information

Machine Learning. Linear Models. Fabio Vandin October 10, 2017

Machine Learning. Linear Models. Fabio Vandin October 10, 2017 Machine Learning Linear Models Fabio Vandin October 10, 2017 1 Linear Predictors and Affine Functions Consider X = R d Affine functions: L d = {h w,b : w R d, b R} where ( d ) h w,b (x) = w, x + b = w

More information

WHY ARE DEEP NETS REVERSIBLE: A SIMPLE THEORY,

WHY ARE DEEP NETS REVERSIBLE: A SIMPLE THEORY, WHY ARE DEEP NETS REVERSIBLE: A SIMPLE THEORY, WITH IMPLICATIONS FOR TRAINING Sanjeev Arora, Yingyu Liang & Tengyu Ma Department of Computer Science Princeton University Princeton, NJ 08540, USA {arora,yingyul,tengyu}@cs.princeton.edu

More information

Learning with multiple models. Boosting.

Learning with multiple models. Boosting. CS 2750 Machine Learning Lecture 21 Learning with multiple models. Boosting. Milos Hauskrecht milos@cs.pitt.edu 5329 Sennott Square Learning with multiple models: Approach 2 Approach 2: use multiple models

More information

Data Mining und Maschinelles Lernen

Data Mining und Maschinelles Lernen Data Mining und Maschinelles Lernen Ensemble Methods Bias-Variance Trade-off Basic Idea of Ensembles Bagging Basic Algorithm Bagging with Costs Randomization Random Forests Boosting Stacking Error-Correcting

More information

Support vector machines Lecture 4

Support vector machines Lecture 4 Support vector machines Lecture 4 David Sontag New York University Slides adapted from Luke Zettlemoyer, Vibhav Gogate, and Carlos Guestrin Q: What does the Perceptron mistake bound tell us? Theorem: The

More information

PAC-Bayes Risk Bounds for Sample-Compressed Gibbs Classifiers

PAC-Bayes Risk Bounds for Sample-Compressed Gibbs Classifiers PAC-Bayes Ris Bounds for Sample-Compressed Gibbs Classifiers François Laviolette Francois.Laviolette@ift.ulaval.ca Mario Marchand Mario.Marchand@ift.ulaval.ca Département d informatique et de génie logiciel,

More information

Machine Learning. Linear Models. Fabio Vandin October 10, 2017

Machine Learning. Linear Models. Fabio Vandin October 10, 2017 Machine Learning Linear Models Fabio Vandin October 10, 2017 1 Linear Predictors and Affine Functions Consider X = R d Affine functions: L d = {h w,b : w R d, b R} where ( d ) h w,b (x) = w, x + b = w

More information

Neural networks and optimization

Neural networks and optimization Neural networks and optimization Nicolas Le Roux Criteo 18/05/15 Nicolas Le Roux (Criteo) Neural networks and optimization 18/05/15 1 / 85 1 Introduction 2 Deep networks 3 Optimization 4 Convolutional

More information

Denoising Autoencoders

Denoising Autoencoders Denoising Autoencoders Oliver Worm, Daniel Leinfelder 20.11.2013 Oliver Worm, Daniel Leinfelder Denoising Autoencoders 20.11.2013 1 / 11 Introduction Poor initialisation can lead to local minima 1986 -

More information

Deep Learning: a gentle introduction

Deep Learning: a gentle introduction Deep Learning: a gentle introduction Jamal Atif jamal.atif@dauphine.fr PSL, Université Paris-Dauphine, LAMSADE February 8, 206 Jamal Atif (Université Paris-Dauphine) Deep Learning February 8, 206 / Why

More information

Logistic Regression Trained with Different Loss Functions. Discussion

Logistic Regression Trained with Different Loss Functions. Discussion Logistic Regression Trained with Different Loss Functions Discussion CS640 Notations We restrict our discussions to the binary case. g(z) = g (z) = g(z) z h w (x) = g(wx) = + e z = g(z)( g(z)) + e wx =

More information

Apprentissage, réseaux de neurones et modèles graphiques (RCP209) Neural Networks and Deep Learning

Apprentissage, réseaux de neurones et modèles graphiques (RCP209) Neural Networks and Deep Learning Apprentissage, réseaux de neurones et modèles graphiques (RCP209) Neural Networks and Deep Learning Nicolas Thome Prenom.Nom@cnam.fr http://cedric.cnam.fr/vertigo/cours/ml2/ Département Informatique Conservatoire

More information

arxiv: v2 [cs.lg] 27 Oct 2017

arxiv: v2 [cs.lg] 27 Oct 2017 MULTIPLE SOURCE DOMAIN ADAPTATION WITH ADVERSARIAL LEARNING Multiple Source Domain Adaptation with Adversarial Learning arxiv:1705.09684v2 [cs.lg] 27 Oct 2017 Han Zhao Shanghang Zhang Guanhang Wu João

More information

Neural Networks, Computation Graphs. CMSC 470 Marine Carpuat

Neural Networks, Computation Graphs. CMSC 470 Marine Carpuat Neural Networks, Computation Graphs CMSC 470 Marine Carpuat Binary Classification with a Multi-layer Perceptron φ A = 1 φ site = 1 φ located = 1 φ Maizuru = 1 φ, = 2 φ in = 1 φ Kyoto = 1 φ priest = 0 φ

More information

Discriminative Models

Discriminative Models No.5 Discriminative Models Hui Jiang Department of Electrical Engineering and Computer Science Lassonde School of Engineering York University, Toronto, Canada Outline Generative vs. Discriminative models

More information

Sample complexity bounds for differentially private learning

Sample complexity bounds for differentially private learning Sample complexity bounds for differentially private learning Kamalika Chaudhuri University of California, San Diego Daniel Hsu Microsoft Research Outline 1. Learning and privacy model 2. Our results: sample

More information

Neural Networks: Backpropagation

Neural Networks: Backpropagation Neural Networks: Backpropagation Machine Learning Fall 2017 Based on slides and material from Geoffrey Hinton, Richard Socher, Dan Roth, Yoav Goldberg, Shai Shalev-Shwartz and Shai Ben-David, and others

More information

Variations sur la borne PAC-bayésienne

Variations sur la borne PAC-bayésienne Variations sur la borne PAC-bayésienne Pascal Germain INRIA Paris Équipe SIRRA Séminaires du département d informatique et de génie logiciel Université Laval 11 juillet 2016 Pascal Germain INRIA/SIRRA

More information

PAC-learning, VC Dimension and Margin-based Bounds

PAC-learning, VC Dimension and Margin-based Bounds More details: General: http://www.learning-with-kernels.org/ Example of more complex bounds: http://www.research.ibm.com/people/t/tzhang/papers/jmlr02_cover.ps.gz PAC-learning, VC Dimension and Margin-based

More information

Warm up: risk prediction with logistic regression

Warm up: risk prediction with logistic regression Warm up: risk prediction with logistic regression Boss gives you a bunch of data on loans defaulting or not: {(x i,y i )} n i= x i 2 R d, y i 2 {, } You model the data as: P (Y = y x, w) = + exp( yw T

More information

PAC-learning, VC Dimension and Margin-based Bounds

PAC-learning, VC Dimension and Margin-based Bounds More details: General: http://www.learning-with-kernels.org/ Example of more complex bounds: http://www.research.ibm.com/people/t/tzhang/papers/jmlr02_cover.ps.gz PAC-learning, VC Dimension and Margin-based

More information

Model Averaging With Holdout Estimation of the Posterior Distribution

Model Averaging With Holdout Estimation of the Posterior Distribution Model Averaging With Holdout stimation of the Posterior Distribution Alexandre Lacoste alexandre.lacoste.1@ulaval.ca François Laviolette francois.laviolette@ift.ulaval.ca Mario Marchand mario.marchand@ift.ulaval.ca

More information

Machine Learning Basics Lecture 7: Multiclass Classification. Princeton University COS 495 Instructor: Yingyu Liang

Machine Learning Basics Lecture 7: Multiclass Classification. Princeton University COS 495 Instructor: Yingyu Liang Machine Learning Basics Lecture 7: Multiclass Classification Princeton University COS 495 Instructor: Yingyu Liang Example: image classification indoor Indoor outdoor Example: image classification (multiclass)

More information

arxiv: v1 [cs.lg] 4 Feb 2014

arxiv: v1 [cs.lg] 4 Feb 2014 arxiv:140796v1 [cs.lg] 4 Feb 2014 Alexandre Lacoste ALEXANDRE.LACOSTE.1@ULAVAL.CA Département d informatique et de génie logiciel, Université Laval, Québec, Canada, G1K-7P4 Hugo Larochelle HUGO.LAROCHELLE@USHERBROOKE.CA

More information

Towards a Data-driven Approach to Exploring Galaxy Evolution via Generative Adversarial Networks

Towards a Data-driven Approach to Exploring Galaxy Evolution via Generative Adversarial Networks Towards a Data-driven Approach to Exploring Galaxy Evolution via Generative Adversarial Networks Tian Li tian.li@pku.edu.cn EECS, Peking University Abstract Since laboratory experiments for exploring astrophysical

More information

UNSUPERVISED LEARNING

UNSUPERVISED LEARNING UNSUPERVISED LEARNING Topics Layer-wise (unsupervised) pre-training Restricted Boltzmann Machines Auto-encoders LAYER-WISE (UNSUPERVISED) PRE-TRAINING Breakthrough in 2006 Layer-wise (unsupervised) pre-training

More information

Two transfer learning approaches for domain adaptation

Two transfer learning approaches for domain adaptation Two transfer learning approaches for domain adaptation Amaury Habrard amaury.habrard@univ-st-etienne.fr Laboratoire Hubert Curien, UMR CNRS 5516 University Jean Monnet - Saint-Étienne (France) Seminar,

More information

From PAC-Bayes Bounds to Quadratic Programs for Majority Votes

From PAC-Bayes Bounds to Quadratic Programs for Majority Votes François Laviolette FrancoisLaviolette@iftulavalca Mario Marchand MarioMarchand@iftulavalca Jean-Francis Roy Jean-FrancisRoy1@ulavalca Département d informatique et de génie logiciel, Université Laval,

More information

Machine learning comes from Bayesian decision theory in statistics. There we want to minimize the expected value of the loss function.

Machine learning comes from Bayesian decision theory in statistics. There we want to minimize the expected value of the loss function. Bayesian learning: Machine learning comes from Bayesian decision theory in statistics. There we want to minimize the expected value of the loss function. Let y be the true label and y be the predicted

More information

Discriminative Models

Discriminative Models No.5 Discriminative Models Hui Jiang Department of Electrical Engineering and Computer Science Lassonde School of Engineering York University, Toronto, Canada Outline Generative vs. Discriminative models

More information

Domain Adaptation of Majority Votes via Perturbed Variation-based Label Transfer

Domain Adaptation of Majority Votes via Perturbed Variation-based Label Transfer Domain Adaptation of Majority Votes via Perturbed Variation-based Label Transfer Emilie Morvant To cite this version: Emilie Morvant. Domain Adaptation of Majority Votes via Perturbed Variation-based Label

More information

La théorie PAC-Bayes en apprentissage supervisé

La théorie PAC-Bayes en apprentissage supervisé La théorie PAC-Bayes en apprentissage supervisé Présentation au LRI de l université Paris XI François Laviolette, Laboratoire du GRAAL, Université Laval, Québec, Canada 14 dcembre 2010 Summary Aujourd

More information

Machine Learning Basics

Machine Learning Basics Security and Fairness of Deep Learning Machine Learning Basics Anupam Datta CMU Spring 2019 Image Classification Image Classification Image classification pipeline Input: A training set of N images, each

More information

Statistical Machine Learning from Data

Statistical Machine Learning from Data Samy Bengio Statistical Machine Learning from Data 1 Statistical Machine Learning from Data Ensembles Samy Bengio IDIAP Research Institute, Martigny, Switzerland, and Ecole Polytechnique Fédérale de Lausanne

More information

Machine Learning. Lecture 9: Learning Theory. Feng Li.

Machine Learning. Lecture 9: Learning Theory. Feng Li. Machine Learning Lecture 9: Learning Theory Feng Li fli@sdu.edu.cn https://funglee.github.io School of Computer Science and Technology Shandong University Fall 2018 Why Learning Theory How can we tell

More information

The sample complexity of agnostic learning with deterministic labels

The sample complexity of agnostic learning with deterministic labels The sample complexity of agnostic learning with deterministic labels Shai Ben-David Cheriton School of Computer Science University of Waterloo Waterloo, ON, N2L 3G CANADA shai@uwaterloo.ca Ruth Urner College

More information

Generalization Bounds in Machine Learning. Presented by: Afshin Rostamizadeh

Generalization Bounds in Machine Learning. Presented by: Afshin Rostamizadeh Generalization Bounds in Machine Learning Presented by: Afshin Rostamizadeh Outline Introduction to generalization bounds. Examples: VC-bounds Covering Number bounds Rademacher bounds Stability bounds

More information

Machine Learning. Computational Learning Theory. Le Song. CSE6740/CS7641/ISYE6740, Fall 2012

Machine Learning. Computational Learning Theory. Le Song. CSE6740/CS7641/ISYE6740, Fall 2012 Machine Learning CSE6740/CS7641/ISYE6740, Fall 2012 Computational Learning Theory Le Song Lecture 11, September 20, 2012 Based on Slides from Eric Xing, CMU Reading: Chap. 7 T.M book 1 Complexity of Learning

More information

Maximum Margin Interval Trees

Maximum Margin Interval Trees Maximum Margin Interval Trees Alexandre Drouin Département d informatique et de génie logiciel Université Laval, Québec, Canada alexandre.drouin.8@ulaval.ca Toby Dylan Hocking McGill Genome Center McGill

More information

arxiv: v1 [stat.ml] 3 Nov 2015

arxiv: v1 [stat.ml] 3 Nov 2015 Under review as a conference paper at ICLR 6 THE VARIATIONAL FAIR AUTO ENCODER Christos Louizos, Kevin Swersky, Yujia Li, Ma Welling, Richard Zemel Machine Learning Group, University of Amsterdam Department

More information

STATISTICAL BEHAVIOR AND CONSISTENCY OF CLASSIFICATION METHODS BASED ON CONVEX RISK MINIMIZATION

STATISTICAL BEHAVIOR AND CONSISTENCY OF CLASSIFICATION METHODS BASED ON CONVEX RISK MINIMIZATION STATISTICAL BEHAVIOR AND CONSISTENCY OF CLASSIFICATION METHODS BASED ON CONVEX RISK MINIMIZATION Tong Zhang The Annals of Statistics, 2004 Outline Motivation Approximation error under convex risk minimization

More information

MIRA, SVM, k-nn. Lirong Xia

MIRA, SVM, k-nn. Lirong Xia MIRA, SVM, k-nn Lirong Xia Linear Classifiers (perceptrons) Inputs are feature values Each feature has a weight Sum is the activation activation w If the activation is: Positive: output +1 Negative, output

More information

CS 188: Artificial Intelligence. Outline

CS 188: Artificial Intelligence. Outline CS 188: Artificial Intelligence Lecture 21: Perceptrons Pieter Abbeel UC Berkeley Many slides adapted from Dan Klein. Outline Generative vs. Discriminative Binary Linear Classifiers Perceptron Multi-class

More information

Feature Design. Feature Design. Feature Design. & Deep Learning

Feature Design. Feature Design. Feature Design. & Deep Learning Artificial Intelligence and its applications Lecture 9 & Deep Learning Professor Daniel Yeung danyeung@ieee.org Dr. Patrick Chan patrickchan@ieee.org South China University of Technology, China Appropriately

More information

CS 6501: Deep Learning for Computer Graphics. Basics of Neural Networks. Connelly Barnes

CS 6501: Deep Learning for Computer Graphics. Basics of Neural Networks. Connelly Barnes CS 6501: Deep Learning for Computer Graphics Basics of Neural Networks Connelly Barnes Overview Simple neural networks Perceptron Feedforward neural networks Multilayer perceptron and properties Autoencoders

More information

SGD and Deep Learning

SGD and Deep Learning SGD and Deep Learning Subgradients Lets make the gradient cheating more formal. Recall that the gradient is the slope of the tangent. f(w 1 )+rf(w 1 ) (w w 1 ) Non differentiable case? w 1 Subgradients

More information

AdaBoost. Lecturer: Authors: Center for Machine Perception Czech Technical University, Prague

AdaBoost. Lecturer: Authors: Center for Machine Perception Czech Technical University, Prague AdaBoost Lecturer: Jan Šochman Authors: Jan Šochman, Jiří Matas Center for Machine Perception Czech Technical University, Prague http://cmp.felk.cvut.cz Motivation Presentation 2/17 AdaBoost with trees

More information

Deep learning / Ian Goodfellow, Yoshua Bengio and Aaron Courville. - Cambridge, MA ; London, Spis treści

Deep learning / Ian Goodfellow, Yoshua Bengio and Aaron Courville. - Cambridge, MA ; London, Spis treści Deep learning / Ian Goodfellow, Yoshua Bengio and Aaron Courville. - Cambridge, MA ; London, 2017 Spis treści Website Acknowledgments Notation xiii xv xix 1 Introduction 1 1.1 Who Should Read This Book?

More information

Selective Prediction. Binary classifications. Rong Zhou November 8, 2017

Selective Prediction. Binary classifications. Rong Zhou November 8, 2017 Selective Prediction Binary classifications Rong Zhou November 8, 2017 Table of contents 1. What are selective classifiers? 2. The Realizable Setting 3. The Noisy Setting 1 What are selective classifiers?

More information

CSE 417T: Introduction to Machine Learning. Lecture 11: Review. Henry Chai 10/02/18

CSE 417T: Introduction to Machine Learning. Lecture 11: Review. Henry Chai 10/02/18 CSE 417T: Introduction to Machine Learning Lecture 11: Review Henry Chai 10/02/18 Unknown Target Function!: # % Training data Formal Setup & = ( ), + ),, ( -, + - Learning Algorithm 2 Hypothesis Set H

More information

CMU-Q Lecture 24:

CMU-Q Lecture 24: CMU-Q 15-381 Lecture 24: Supervised Learning 2 Teacher: Gianni A. Di Caro SUPERVISED LEARNING Hypotheses space Hypothesis function Labeled Given Errors Performance criteria Given a collection of input

More information

Sparse Domain Adaptation in a Good Similarity-Based Projection Space

Sparse Domain Adaptation in a Good Similarity-Based Projection Space Sparse Domain Adaptation in a Good Similarity-Based Projection Space Emilie Morvant, Amaury Habrard, Stéphane Ayache To cite this version: Emilie Morvant, Amaury Habrard, Stéphane Ayache. Sparse Domain

More information

CS534 Machine Learning - Spring Final Exam

CS534 Machine Learning - Spring Final Exam CS534 Machine Learning - Spring 2013 Final Exam Name: You have 110 minutes. There are 6 questions (8 pages including cover page). If you get stuck on one question, move on to others and come back to the

More information

Greedy Biomarker Discovery in the Genome with Applications to Antibiotic Resistance

Greedy Biomarker Discovery in the Genome with Applications to Antibiotic Resistance Greedy Biomarker Discovery in the Genome with Applications to Antibiotic Resistance Alexandre Drouin, Sébastien Giguère, Maxime Déraspe, François Laviolette, Mario Marchand, Jacques Corbeil Department

More information

ECS171: Machine Learning

ECS171: Machine Learning ECS171: Machine Learning Lecture 3: Linear Models I (LFD 3.2, 3.3) Cho-Jui Hsieh UC Davis Jan 17, 2018 Linear Regression (LFD 3.2) Regression Classification: Customer record Yes/No Regression: predicting

More information

Towards Lifelong Machine Learning Multi-Task and Lifelong Learning with Unlabeled Tasks Christoph Lampert

Towards Lifelong Machine Learning Multi-Task and Lifelong Learning with Unlabeled Tasks Christoph Lampert Towards Lifelong Machine Learning Multi-Task and Lifelong Learning with Unlabeled Tasks Christoph Lampert HSE Computer Science Colloquium September 6, 2016 IST Austria (Institute of Science and Technology

More information

Lecture Support Vector Machine (SVM) Classifiers

Lecture Support Vector Machine (SVM) Classifiers Introduction to Machine Learning Lecturer: Amir Globerson Lecture 6 Fall Semester Scribe: Yishay Mansour 6.1 Support Vector Machine (SVM) Classifiers Classification is one of the most important tasks in

More information

CS7267 MACHINE LEARNING

CS7267 MACHINE LEARNING CS7267 MACHINE LEARNING ENSEMBLE LEARNING Ref: Dr. Ricardo Gutierrez-Osuna at TAMU, and Aarti Singh at CMU Mingon Kang, Ph.D. Computer Science, Kennesaw State University Definition of Ensemble Learning

More information

TUTORIAL PART 1 Unsupervised Learning

TUTORIAL PART 1 Unsupervised Learning TUTORIAL PART 1 Unsupervised Learning Marc'Aurelio Ranzato Department of Computer Science Univ. of Toronto ranzato@cs.toronto.edu Co-organizers: Honglak Lee, Yoshua Bengio, Geoff Hinton, Yann LeCun, Andrew

More information

Linear classifiers Lecture 3

Linear classifiers Lecture 3 Linear classifiers Lecture 3 David Sontag New York University Slides adapted from Luke Zettlemoyer, Vibhav Gogate, and Carlos Guestrin ML Methodology Data: labeled instances, e.g. emails marked spam/ham

More information

From perceptrons to word embeddings. Simon Šuster University of Groningen

From perceptrons to word embeddings. Simon Šuster University of Groningen From perceptrons to word embeddings Simon Šuster University of Groningen Outline A basic computational unit Weighting some input to produce an output: classification Perceptron Classify tweets Written

More information

Manual for a computer class in ML

Manual for a computer class in ML Manual for a computer class in ML November 3, 2015 Abstract This document describes a tour of Machine Learning (ML) techniques using tools in MATLAB. We point to the standard implementations, give example

More information

Restricted Boltzmann Machines

Restricted Boltzmann Machines Restricted Boltzmann Machines http://deeplearning4.org/rbm-mnist-tutorial.html Slides from Hugo Larochelle, Geoffrey Hinton, and Yoshua Bengio CSC321: Intro to Machine Learning and Neural Networks, Winter

More information

Logistic Regression. Machine Learning Fall 2018

Logistic Regression. Machine Learning Fall 2018 Logistic Regression Machine Learning Fall 2018 1 Where are e? We have seen the folloing ideas Linear models Learning as loss minimization Bayesian learning criteria (MAP and MLE estimation) The Naïve Bayes

More information

Machine Learning and Related Disciplines

Machine Learning and Related Disciplines Machine Learning and Related Disciplines The 15 th Winter School of Statistical Physics POSCO International Center & POSTECH, Pohang 2018. 1. 8-12 (Mon.-Fri.) Yung-Kyun Noh Machine Learning Interdisciplinary

More information

Foundations of Machine Learning

Foundations of Machine Learning Introduction to ML Mehryar Mohri Courant Institute and Google Research mohri@cims.nyu.edu page 1 Logistics Prerequisites: basics in linear algebra, probability, and analysis of algorithms. Workload: about

More information

Need for Deep Networks Perceptron. Can only model linear functions. Kernel Machines. Non-linearity provided by kernels

Need for Deep Networks Perceptron. Can only model linear functions. Kernel Machines. Non-linearity provided by kernels Need for Deep Networks Perceptron Can only model linear functions Kernel Machines Non-linearity provided by kernels Need to design appropriate kernels (possibly selecting from a set, i.e. kernel learning)

More information

Computational Learning Theory. CS534 - Machine Learning

Computational Learning Theory. CS534 - Machine Learning Computational Learning Theory CS534 Machine Learning Introduction Computational learning theory Provides a theoretical analysis of learning Shows when a learning algorithm can be expected to succeed Shows

More information

Numerical Learning Algorithms

Numerical Learning Algorithms Numerical Learning Algorithms Example SVM for Separable Examples.......................... Example SVM for Nonseparable Examples....................... 4 Example Gaussian Kernel SVM...............................

More information

Bagging and Other Ensemble Methods

Bagging and Other Ensemble Methods Bagging and Other Ensemble Methods Sargur N. Srihari srihari@buffalo.edu 1 Regularization Strategies 1. Parameter Norm Penalties 2. Norm Penalties as Constrained Optimization 3. Regularization and Underconstrained

More information

The PAC Learning Framework -II

The PAC Learning Framework -II The PAC Learning Framework -II Prof. Dan A. Simovici UMB 1 / 1 Outline 1 Finite Hypothesis Space - The Inconsistent Case 2 Deterministic versus stochastic scenario 3 Bayes Error and Noise 2 / 1 Outline

More information

arxiv: v1 [stat.ml] 17 Jul 2017

arxiv: v1 [stat.ml] 17 Jul 2017 PACBayes and Domain Adaptation arxiv:1707.05712v1 [stat.ml] 17 Jul 2017 Pascal Germain pascal.germain@inria.fr Département d informatique de l ENS, École normale supérieure, CNRS, PSL Research University,

More information

Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICA

Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICA Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICA with Hiroshi Morioka Dept of Computer Science University of Helsinki, Finland Facebook AI Summit, 13th June 2016 Abstract

More information

PAC Learning Introduction to Machine Learning. Matt Gormley Lecture 14 March 5, 2018

PAC Learning Introduction to Machine Learning. Matt Gormley Lecture 14 March 5, 2018 10-601 Introduction to Machine Learning Machine Learning Department School of Computer Science Carnegie Mellon University PAC Learning Matt Gormley Lecture 14 March 5, 2018 1 ML Big Picture Learning Paradigms:

More information

Reducing Multiclass to Binary: A Unifying Approach for Margin Classifiers

Reducing Multiclass to Binary: A Unifying Approach for Margin Classifiers Reducing Multiclass to Binary: A Unifying Approach for Margin Classifiers Erin Allwein, Robert Schapire and Yoram Singer Journal of Machine Learning Research, 1:113-141, 000 CSE 54: Seminar on Learning

More information

Active Learning and Optimized Information Gathering

Active Learning and Optimized Information Gathering Active Learning and Optimized Information Gathering Lecture 7 Learning Theory CS 101.2 Andreas Krause Announcements Project proposal: Due tomorrow 1/27 Homework 1: Due Thursday 1/29 Any time is ok. Office

More information

Lecture 14: Deep Generative Learning

Lecture 14: Deep Generative Learning Generative Modeling CSED703R: Deep Learning for Visual Recognition (2017F) Lecture 14: Deep Generative Learning Density estimation Reconstructing probability density function using samples Bohyung Han

More information

Classification objectives COMS 4771

Classification objectives COMS 4771 Classification objectives COMS 4771 1. Recap: binary classification Scoring functions Consider binary classification problems with Y = { 1, +1}. 1 / 22 Scoring functions Consider binary classification

More information

CS446: Machine Learning Fall Final Exam. December 6 th, 2016

CS446: Machine Learning Fall Final Exam. December 6 th, 2016 CS446: Machine Learning Fall 2016 Final Exam December 6 th, 2016 This is a closed book exam. Everything you need in order to solve the problems is supplied in the body of this exam. This exam booklet contains

More information

How to do backpropagation in a brain

How to do backpropagation in a brain How to do backpropagation in a brain Geoffrey Hinton Canadian Institute for Advanced Research & University of Toronto & Google Inc. Prelude I will start with three slides explaining a popular type of deep

More information

Ensembles. Léon Bottou COS 424 4/8/2010

Ensembles. Léon Bottou COS 424 4/8/2010 Ensembles Léon Bottou COS 424 4/8/2010 Readings T. G. Dietterich (2000) Ensemble Methods in Machine Learning. R. E. Schapire (2003): The Boosting Approach to Machine Learning. Sections 1,2,3,4,6. Léon

More information

The Perceptron algorithm

The Perceptron algorithm The Perceptron algorithm Tirgul 3 November 2016 Agnostic PAC Learnability A hypothesis class H is agnostic PAC learnable if there exists a function m H : 0,1 2 N and a learning algorithm with the following

More information

10-701/ Machine Learning - Midterm Exam, Fall 2010

10-701/ Machine Learning - Midterm Exam, Fall 2010 10-701/15-781 Machine Learning - Midterm Exam, Fall 2010 Aarti Singh Carnegie Mellon University 1. Personal info: Name: Andrew account: E-mail address: 2. There should be 15 numbered pages in this exam

More information

Risk Bounds for the Majority Vote: From a PAC-Bayesian Analysis to a Learning Algorithm

Risk Bounds for the Majority Vote: From a PAC-Bayesian Analysis to a Learning Algorithm Journal of Machine Learning Research 16 2015 787-860 Submitted 5/13; Revised 9/14; Published 4/15 Risk Bounds for the Majority Vote: From a PAC-Bayesian Analysis to a Learning Algorithm Pascal Germain

More information

Need for Deep Networks Perceptron. Can only model linear functions. Kernel Machines. Non-linearity provided by kernels

Need for Deep Networks Perceptron. Can only model linear functions. Kernel Machines. Non-linearity provided by kernels Need for Deep Networks Perceptron Can only model linear functions Kernel Machines Non-linearity provided by kernels Need to design appropriate kernels (possibly selecting from a set, i.e. kernel learning)

More information

CSE 417T: Introduction to Machine Learning. Final Review. Henry Chai 12/4/18

CSE 417T: Introduction to Machine Learning. Final Review. Henry Chai 12/4/18 CSE 417T: Introduction to Machine Learning Final Review Henry Chai 12/4/18 Overfitting Overfitting is fitting the training data more than is warranted Fitting noise rather than signal 2 Estimating! "#$

More information

Statistical and Computational Learning Theory

Statistical and Computational Learning Theory Statistical and Computational Learning Theory Fundamental Question: Predict Error Rates Given: Find: The space H of hypotheses The number and distribution of the training examples S The complexity of the

More information

Support Vector Machines

Support Vector Machines Support Vector Machines Le Song Machine Learning I CSE 6740, Fall 2013 Naïve Bayes classifier Still use Bayes decision rule for classification P y x = P x y P y P x But assume p x y = 1 is fully factorized

More information

PAC-Bayesian Generalization Bound for Multi-class Learning

PAC-Bayesian Generalization Bound for Multi-class Learning PAC-Bayesian Generalization Bound for Multi-class Learning Loubna BENABBOU Department of Industrial Engineering Ecole Mohammadia d Ingènieurs Mohammed V University in Rabat, Morocco Benabbou@emi.ac.ma

More information

Empirical Risk Minimization

Empirical Risk Minimization Empirical Risk Minimization Fabrice Rossi SAMM Université Paris 1 Panthéon Sorbonne 2018 Outline Introduction PAC learning ERM in practice 2 General setting Data X the input space and Y the output space

More information