THE STATE OF CONTEMPORARY COMPUTING SUBSTRATES FOR OPTIMIZATION METHODS. Benjamin Recht UC Berkeley
|
|
- Lynette Bryan
- 5 years ago
- Views:
Transcription
1 THE STATE OF CONTEMPORARY COMPUTING SUBSTRATES FOR OPTIMIZATION METHODS Benjamin Recht UC Berkeley
2 MY QUIXOTIC QUEST FOR SUPERLINEAR ALGORITHMS Benjamin Recht UC Berkeley
3 Collaborators Slides extracted by torturing Eric Jonas, Vaishaal Shankar, Stephen Tu, Shivaram Venkataraman, and Ashia Wilson
4 The holy grail of optimization Fix a positive definite, n x n matrix A Find x such that Ax = b minimize 1 2 xt Ax b T x Linear regression/classification Interior Point Methods Sum of Squares Quadratic Programming Sequential Quadratic Programming Newton s Method Hard case for Nesterov Dense case ~ bigger sparse cases
5 Iterative Solvers Fix a positive definite, n x n matrix A Find x such that Ax = b complexity = (number of iterations) x (flops per iteration) L O µ log(1/ ) O(n 2 ) x k+1 = x k s(ax k b) Steepest Descent
6 Iterative Solvers Fix a positive definite, n x n matrix A Find x such that Ax = b complexity = (number of iterations) x (flops per iteration) O n L max µ log(1/ ) O(n) x (i) k+1 = x(i) k A 1 ii (at i x k b i ) Coordinate Descent (Gauss-Seidel)
7 Iterative Solvers Fix a positive definite, n x n matrix A Find x such that Ax = b complexity = (number of iterations) x (flops per iteration) O n 2 K(A) log(1/ ) Not sublinear in dimension. direct solve complexity = O(n 3 )
8 Iterative or Direct? Fix a positive definite, n x n matrix A n=60,000 Find x such that Ax = b b 60,000 x 10 iterative complexity O n 2 K(A) log(1/ ) direct solve complexity = O(n 3 ) direct solve wall clock = 111s iterative wall clock = 127s kx x? k F =0.58 kx? k F Are we selling ourselves short with these crummy iterative methods?
9 Why is direct faster? iterative complexity O n 2 K(A) log(1/ ) direct solve complexity = O(n 3 ) n=60,000 b 60,000 x 10 direct solve wall clock = 111s iterative wall clock = 127s kx x? k F =0.58 kx? k F Are we selling ourselves short with these crummy iterative methods? To achieve maximum speed, data shuffling is required Memory bandwidth is critical Maybe we just need more RAM?
10 I NEED MOAR RAM Superlinear scaling is the worst. n RAM Time Memory demand growing quadratically means more than 60,000 30GB 111s one computer is needed for anything larger than 400K. 350K 1TB 6 hours Cubic time scaling means a lot 1.2M 12TB 10 days of cores are needed to minimize time. Time extrapolation based on 64 cores, 2TB RAM Where can I get all of this compute?
11 THE CLOUD
12 Cloud Computing CHOICEs t2.nano, t2.micro, t2.small m4.large, m4.xlarge, m4.2xlarge, m4.4xlarge, m3.medium, c4.large, c4.xlarge, c4.2xlarge, c3.large, c3.xlarge, c3.4xlarge, r3.large, r3.xlarge, r3.4xlarge, i2.2xlarge, i2.4xlarge, d2.xlarge d2.2xlarge, d2.4xlarge, Basic tier: A0, A1, A2, A3, A4 Optimized Compute : D1, D2, D3, D4, D11, D12, D13 D1v2, D2v2, D3v2, D11v2, Latest CPUs: G1, G2, G3, Network Optimized: A8, A9 Compute Intensive: A10, A11, n1-standard-1, ns1-standard-2, ns1- standard-4, ns1-standard-8, ns1- standard-16, ns1highmem-2, ns1- highmem-4, ns1-highmem-8, n1- highcpu-2, n1-highcpu-4, n1-highcpu-8, n1-highcpu-16, n1-highcpu-32, f1-micro, g1-small Amazon EC2 Microsoft Azure Google Cloud Engine
13
14 TYRANNY of CHOICE
15 #THECLOUDISTOODAMNHARD What type? what instance? What base image? What is the cheapest configuration to run my job in 2 hours? How many to spin up? What price? spot? wait, Wait, WAIT oh god
16 Do choices matter? Equal Price/Hour, Aggregate Cores QR Factorization:1M by 1K 1 r3.8xlarge r3.4xlarge 4 r3.2xlarge 8 r3.xlarge 16 r3.large Time (s) Mem BW (GB/s) 150 ~2x performance difference for same price
17 Do choices MATTER? r3.4xlarge instances, QR Factorization:1M by 1K 30 Actual Ideal 22.5 Time (s) computation + communication yield non-linear scaling Cores 17
18 Computation patterns Time INPUT Time 1 machines
19 Communication Patterns ONE-To-ONE Tree DAG All-to-one CONSTANT LOG LINEAR 19
20 BASIC Model Computation (linear) All-to-One DAG input time= x 1 + x 2 machines + x 3 log(machines)+ x 4 (machines) Serial Tree DAG Execution Collect Training Data Fit Linear Regression
21 Optimal Design of Experiments Given a Linear Model y i = a T i x + w i, i =1,...,m Collection of (input, machines) Associate cost with each experiment λ i - Fraction of times each experiment is run minimize tr n Pm i=1 ia i a T i 1 o Lower variance! Better model i 2 [0, 1] P m I=1 c i i apple B Bound total cost
22 Number of instances Large Least-squares solve (TIMIT) on r3.xlarge instances Predicted Actual Time per iteration (s) Machines Machines
23 CHOOSING INSTANCE TYPES Running Time Training 8 r3.4xlarge r3.2xlarge r3.xlarge Time (seconds)
24 Wait. That still seems hard! and what happened to the RAM?
25 AWS LAMBDA 300 seconds single-core (AVX2) 512 MB in /tmp 1.5GB RAM Python, Java, Node S3 = Simple Storage Service. Essentially infinite RAM Communication at 600MB/s per machine (same speed as SATA) (PCI Bus is 1GB/s, Memory Bus is 80GB/s)
26 AWS LAMBDA 300 seconds single-core (AVX2) 512 MB in /tmp 1.5GB RAM Python, Java, Node
27 LAMBDA SCALABILITY Compute Data
28 Most wrens are small and rather inconspicuous, except for their loud and often complex songs. pywren
29 THE API
30 How it works future = runner.map(fn, data) Serialize func and data func data data data Put on S3 Invoke Lambda pull job from s3 download anaconda runtime python to run code pickle result stick in S3 future.result() poll S3 unpickle and return your laptop result the cloud
31 How expensive is S3? (Taking dimensionality analysis seriously, or beyond PSPACE ) Simple Storage Service Essentially infinite RAM Communication at 600MB/s per machine Same speed as SATA (PCI Bus is 1GB/s, Memory Bus is 80GB/s)
32 How do algorithms change when you have infinite memory (through a straw) Never discard intermediate information
33 numpywren That s a lot of SIMD cores! Parallel matrix multiplication is easy when output matrix is small D x N = D x D N x D Fits cleanly into map-reduce framework + + = D x D
34 numpywren However when output matrix is very large it becomes very difficult or expensive to store in memory D x N = N x D N x N For example for N = 1e6 and D=1e4 D x D matrix of doubles is 800 Mb N x N matrix of doubles is 8 TB Storing 8 TB in memory traditional cluster is expensive!
35 numpywren N D Lambdas Runtime Output Size N x N s 20 GB s 20 GB Solution: Use S3 to store matrices, stream blocks to Lambdas to compute output matrix in parallel 1.2 Millon 1.2 Million s 11 TB s 11 TB
36 Cholesky in numpywren apple A11 A T 12 A 12 A 22 = apple L11 0 L 12 L 22 apple L T 11 L T 12 0 L T 22 N x N Solution: Use S3 to store matrices, stream blocks to Lambdas to compute output matrix in parallel
37 Cholesky in numpywren apple A11 A T 12 A 12 A 22 = apple L11 0 L 12 L 22 apple L T 11 L T 12 0 L T 22 N x N Solution: Use S3 to store matrices, stream blocks to Lambdas to compute output matrix in parallel
38 Cholesky in numpywren apple A11 A T 12 A 12 A 22 = apple L11 0 L 12 L 22 apple L T 11 L T 12 0 L T 22 N x N Solution: Use S3 to store matrices, stream blocks to Lambdas to compute output matrix in parallel
39 Cholesky in numpywren apple A11 A T 12 A 12 A 22 = apple L11 0 L 12 L 22 apple L T 11 L T 12 0 L T 22 N x N L 21 = A 21 L T 11 Solution: Use S3 to store matrices, stream blocks to Lambdas to compute output matrix in parallel
40 Cholesky in numpywren apple A11 A T 12 A 12 A 22 = apple L11 0 L 12 L 22 apple L T 11 L T 12 0 L T 22 N x N L 21 = A 21 L T 11 Solution: Use S3 to store matrices, stream blocks to Lambdas to compute output matrix in parallel A (new) 22 = A 22 L 12 L T 12
41 The future is direct solves Fix a positive definite, n x n matrix A Find x such that Ax = b minimize 1 2 xt Ax b T x Iterative methods are not fast New substrates make large-scale direct solve reachable Need simpler tools and cost management There are algorithmic challenges in noniterative methods
42 References If you d like to try Pywren visit pywren.io Occupy the Cloud: Distributed Computing for the 99%. Eric Jonas, Qifan Pu, Shivaram Venkataraman, Ion Stoica, and Benjamin Recht. In Proceedings of the ACM Symposium on Cloud Computing (SOCC) Breaking Locality Accelerates Block Gauss-Seidel. Stephen Tu, Shivaram Venkataraman, Ashia C. Wilson, Alex Gittens, Michael I. Jordan, and Benjamin Recht. In Proceedings of the International Conference on Machine Learning (ICML) Ernest: Efficient Performance Prediction for Large Scale Advanced Analytics. Shivaram Venkataraman, Zongheng Yang, Michael J Franklin, Benjamin Recht, and Ion Stoica. In Proceedings of the Symposium on Networked Systems Design (NSDI)
StreamSVM Linear SVMs and Logistic Regression When Data Does Not Fit In Memory
StreamSVM Linear SVMs and Logistic Regression When Data Does Not Fit In Memory S.V. N. (vishy) Vishwanathan Purdue University and Microsoft vishy@purdue.edu October 9, 2012 S.V. N. Vishwanathan (Purdue,
More informationReview: From problem to parallel algorithm
Review: From problem to parallel algorithm Mathematical formulations of interesting problems abound Poisson s equation Sources: Electrostatics, gravity, fluid flow, image processing (!) Numerical solution:
More informationFaster Kernel Ridge Regression Using Sketching and Preconditioning
Faster Kernel Ridge Regression Using Sketching and Preconditioning Haim Avron Department of Applied Math Tel Aviv University, Israel SIAM CS&E 2017 February 27, 2017 Brief Introduction to Kernel Ridge
More informationCloud Performance Benchmark Series
Cloud Performance Benchmark Series EC2 CPU Speed Benchmarks Appendix: Comparison with.com Computing Kalpit Sarda Sumit Sanghrajka Radu Sion ver..7 C l o u d B e n c h m a r k s : A m a z o n E C 2 v s.
More informationPracticality of Large Scale Fast Matrix Multiplication
Practicality of Large Scale Fast Matrix Multiplication Grey Ballard, James Demmel, Olga Holtz, Benjamin Lipshitz and Oded Schwartz UC Berkeley IWASEP June 5, 2012 Napa Valley, CA Research supported by
More informationFAS and Solver Performance
FAS and Solver Performance Matthew Knepley Mathematics and Computer Science Division Argonne National Laboratory Fall AMS Central Section Meeting Chicago, IL Oct 05 06, 2007 M. Knepley (ANL) FAS AMS 07
More information27 : Distributed Monte Carlo Markov Chain. 1 Recap of MCMC and Naive Parallel Gibbs Sampling
10-708: Probabilistic Graphical Models 10-708, Spring 2014 27 : Distributed Monte Carlo Markov Chain Lecturer: Eric P. Xing Scribes: Pengtao Xie, Khoa Luu In this scribe, we are going to review the Parallel
More informationMapReduce in Spark. Krzysztof Dembczyński. Intelligent Decision Support Systems Laboratory (IDSS) Poznań University of Technology, Poland
MapReduce in Spark Krzysztof Dembczyński Intelligent Decision Support Systems Laboratory (IDSS) Poznań University of Technology, Poland Software Development Technologies Master studies, second semester
More informationThis ensures that we walk downhill. For fixed λ not even this may be the case.
Gradient Descent Objective Function Some differentiable function f : R n R. Gradient Descent Start with some x 0, i = 0 and learning rate λ repeat x i+1 = x i λ f(x i ) until f(x i+1 ) ɛ Line Search Variant
More informationUsing R for Iterative and Incremental Processing
Using R for Iterative and Incremental Processing Shivaram Venkataraman, Indrajit Roy, Alvin AuYoung, Robert Schreiber UC Berkeley and HP Labs UC BERKELEY Big Data, Complex Algorithms PageRank (Dominant
More informationFPGA Implementation of a Predictive Controller
FPGA Implementation of a Predictive Controller SIAM Conference on Optimization 2011, Darmstadt, Germany Minisymposium on embedded optimization Juan L. Jerez, George A. Constantinides and Eric C. Kerrigan
More informationClustering algorithms distributed over a Cloud Computing Platform.
Clustering algorithms distributed over a Cloud Computing Platform. SEPTEMBER 28 TH 2012 Ph. D. thesis supervised by Pr. Fabrice Rossi. Matthieu Durut (Telecom/Lokad) 1 / 55 Outline. 1 Introduction to Cloud
More informationCA-SVM: Communication-Avoiding Support Vector Machines on Distributed System
CA-SVM: Communication-Avoiding Support Vector Machines on Distributed System Yang You 1, James Demmel 1, Kent Czechowski 2, Le Song 2, Richard Vuduc 2 UC Berkeley 1, Georgia Tech 2 Yang You (Speaker) James
More informationECS289: Scalable Machine Learning
ECS289: Scalable Machine Learning Cho-Jui Hsieh UC Davis Sept 29, 2016 Outline Convex vs Nonconvex Functions Coordinate Descent Gradient Descent Newton s method Stochastic Gradient Descent Numerical Optimization
More informationRegression. Goal: Learn a mapping from observations (features) to continuous labels given a training set (supervised learning)
Linear Regression Regression Goal: Learn a mapping from observations (features) to continuous labels given a training set (supervised learning) Example: Height, Gender, Weight Shoe Size Audio features
More informationRegression. Goal: Learn a mapping from observations (features) to continuous labels given a training set (supervised learning)
Linear Regression Regression Goal: Learn a mapping from observations (features) to continuous labels given a training set (supervised learning) Example: Height, Gender, Weight Shoe Size Audio features
More informationLarge-Scale Behavioral Targeting
Large-Scale Behavioral Targeting Ye Chen, Dmitry Pavlov, John Canny ebay, Yandex, UC Berkeley (This work was conducted at Yahoo! Labs.) June 30, 2009 Chen et al. (KDD 09) Large-Scale Behavioral Targeting
More informationSMO vs PDCO for SVM: Sequential Minimal Optimization vs Primal-Dual interior method for Convex Objectives for Support Vector Machines
vs for SVM: Sequential Minimal Optimization vs Primal-Dual interior method for Convex Objectives for Support Vector Machines Ding Ma Michael Saunders Working paper, January 5 Introduction In machine learning,
More informationDistributed Machine Learning: A Brief Overview. Dan Alistarh IST Austria
Distributed Machine Learning: A Brief Overview Dan Alistarh IST Austria Background The Machine Learning Cambrian Explosion Key Factors: 1. Large s: Millions of labelled images, thousands of hours of speech
More informationQuasi-Newton Methods
Newton s Method Pros and Cons Quasi-Newton Methods MA 348 Kurt Bryan Newton s method has some very nice properties: It s extremely fast, at least once it gets near the minimum, and with the simple modifications
More informationDistributed Box-Constrained Quadratic Optimization for Dual Linear SVM
Distributed Box-Constrained Quadratic Optimization for Dual Linear SVM Lee, Ching-pei University of Illinois at Urbana-Champaign Joint work with Dan Roth ICML 2015 Outline Introduction Algorithm Experiments
More informationCoded Computation over Heterogeneous Clusters
1 Coded Computation over Heterogeneous Clusters Amirhossein Reisizadeh, Saurav Prakash, Ramtin Pedarsani, Amir Salman Avestimehr University of California, Santa Barbara University of Southern California
More informationArcGIS Enterprise: What s New. Philip Heede Shannon Kalisky Melanie Summers Shreyas Shinde
ArcGIS Enterprise: What s New Philip Heede Shannon Kalisky Melanie Summers Shreyas Shinde ArcGIS Enterprise is the new name for ArcGIS for Server ArcGIS Enterprise Software Components ArcGIS Server Portal
More informationPower System Analysis Prof. A. K. Sinha Department of Electrical Engineering Indian Institute of Technology, Kharagpur. Lecture - 21 Power Flow VI
Power System Analysis Prof. A. K. Sinha Department of Electrical Engineering Indian Institute of Technology, Kharagpur Lecture - 21 Power Flow VI (Refer Slide Time: 00:57) Welcome to lesson 21. In this
More informationS N. hochdimensionaler Lyapunov- und Sylvestergleichungen. Peter Benner. Mathematik in Industrie und Technik Fakultät für Mathematik TU Chemnitz
Ansätze zur numerischen Lösung hochdimensionaler Lyapunov- und Sylvestergleichungen Peter Benner Mathematik in Industrie und Technik Fakultät für Mathematik TU Chemnitz S N SIMULATION www.tu-chemnitz.de/~benner
More informationCHAPTER 11. A Revision. 1. The Computers and Numbers therein
CHAPTER A Revision. The Computers and Numbers therein Traditional computer science begins with a finite alphabet. By stringing elements of the alphabet one after another, one obtains strings. A set of
More informationArcGIS GeoAnalytics Server: An Introduction. Sarah Ambrose and Ravi Narayanan
ArcGIS GeoAnalytics Server: An Introduction Sarah Ambrose and Ravi Narayanan Overview Introduction Demos Analysis Concepts using GeoAnalytics Server GeoAnalytics Data Sources GeoAnalytics Server Administration
More informationParallel programming practices for the solution of Sparse Linear Systems (motivated by computational physics and graphics)
Parallel programming practices for the solution of Sparse Linear Systems (motivated by computational physics and graphics) Eftychios Sifakis CS758 Guest Lecture - 19 Sept 2012 Introduction Linear systems
More informationAMS526: Numerical Analysis I (Numerical Linear Algebra for Computational and Data Sciences)
AMS526: Numerical Analysis I (Numerical Linear Algebra for Computational and Data Sciences) Lecture 19: Computing the SVD; Sparse Linear Systems Xiangmin Jiao Stony Brook University Xiangmin Jiao Numerical
More informationLecture 17: Iterative Methods and Sparse Linear Algebra
Lecture 17: Iterative Methods and Sparse Linear Algebra David Bindel 25 Mar 2014 Logistics HW 3 extended to Wednesday after break HW 4 should come out Monday after break Still need project description
More informationTall-and-skinny! QRs and SVDs in MapReduce
A 1 A 2 A 3 Tall-and-skinny! QRs and SVDs in MapReduce Yangyang Hou " Purdue, CS Austin Benson " Stanford University Paul G. Constantine Col. School. Mines " Joe Nichols U. of Minn James Demmel " UC Berkeley
More informationParallelism in Structured Newton Computations
Parallelism in Structured Newton Computations Thomas F Coleman and Wei u Department of Combinatorics and Optimization University of Waterloo Waterloo, Ontario, Canada N2L 3G1 E-mail: tfcoleman@uwaterlooca
More informationEfficient implementation of the overlap operator on multi-gpus
Efficient implementation of the overlap operator on multi-gpus Andrei Alexandru Mike Lujan, Craig Pelissier, Ben Gamari, Frank Lee SAAHPC 2011 - University of Tennessee Outline Motivation Overlap operator
More informationCS60021: Scalable Data Mining. Large Scale Machine Learning
J. Leskovec, A. Rajaraman, J. Ullman: Mining of Massive Datasets, http://www.mmds.org 1 CS60021: Scalable Data Mining Large Scale Machine Learning Sourangshu Bhattacharya Example: Spam filtering Instance
More informationTraining Support Vector Machines: Status and Challenges
ICML Workshop on Large Scale Learning Challenge July 9, 2008 Chih-Jen Lin (National Taiwan Univ.) 1 / 34 Training Support Vector Machines: Status and Challenges Chih-Jen Lin Department of Computer Science
More informationRandomized Algorithms
Randomized Algorithms Saniv Kumar, Google Research, NY EECS-6898, Columbia University - Fall, 010 Saniv Kumar 9/13/010 EECS6898 Large Scale Machine Learning 1 Curse of Dimensionality Gaussian Mixture Models
More informationERLANGEN REGIONAL COMPUTING CENTER
ERLANGEN REGIONAL COMPUTING CENTER Making Sense of Performance Numbers Georg Hager Erlangen Regional Computing Center (RRZE) Friedrich-Alexander-Universität Erlangen-Nürnberg OpenMPCon 2018 Barcelona,
More informationFastfood Approximating Kernel Expansions in Loglinear Time. Quoc Le, Tamas Sarlos, and Alex Smola Presenter: Shuai Zheng (Kyle)
Fastfood Approximating Kernel Expansions in Loglinear Time Quoc Le, Tamas Sarlos, and Alex Smola Presenter: Shuai Zheng (Kyle) Large Scale Problem: ImageNet Challenge Large scale data Number of training
More informationLeveraging Task-Parallelism in Energy-Efficient ILU Preconditioners
Leveraging Task-Parallelism in Energy-Efficient ILU Preconditioners José I. Aliaga Leveraging task-parallelism in energy-efficient ILU preconditioners Universidad Jaime I (Castellón, Spain) José I. Aliaga
More informationOptimization methods
Optimization methods Optimization-Based Data Analysis http://www.cims.nyu.edu/~cfgranda/pages/obda_spring16 Carlos Fernandez-Granda /8/016 Introduction Aim: Overview of optimization methods that Tend to
More informationTR A Comparison of the Performance of SaP::GPU and Intel s Math Kernel Library (MKL) for Solving Dense Banded Linear Systems
TR-0-07 A Comparison of the Performance of ::GPU and Intel s Math Kernel Library (MKL) for Solving Dense Banded Linear Systems Ang Li, Omkar Deshmukh, Radu Serban, Dan Negrut May, 0 Abstract ::GPU is a
More informationarxiv: v4 [stat.ml] 28 Sep 2017
Parallelizable sparse inverse formulation Gaussian processes (SpInGP) Alexander Grigorievskiy Aalto University, Finland Neil Lawrence University of Sheffield Amazon Research, Cambridge, UK Simo Särkkä
More informationHigher-Order Methods
Higher-Order Methods Stephen J. Wright 1 2 Computer Sciences Department, University of Wisconsin-Madison. PCMI, July 2016 Stephen Wright (UW-Madison) Higher-Order Methods PCMI, July 2016 1 / 25 Smooth
More informationScikit-learn. scikit. Machine learning for the small and the many Gaël Varoquaux. machine learning in Python
Scikit-learn Machine learning for the small and the many Gaël Varoquaux scikit machine learning in Python In this meeting, I represent low performance computing Scikit-learn Machine learning for the small
More informationCompressing Tabular Data via Pairwise Dependencies
Compressing Tabular Data via Pairwise Dependencies Amir Ingber, Yahoo! Research TCE Conference, June 22, 2017 Joint work with Dmitri Pavlichin, Tsachy Weissman (Stanford) Huge datasets: everywhere - Internet
More informationReliability at Scale
Reliability at Scale Intelligent Storage Workshop 5 James Nunez Los Alamos National lab LA-UR-07-0828 & LA-UR-06-0397 May 15, 2007 A Word about scale Petaflop class machines LLNL Blue Gene 350 Tflops 128k
More information1 Overview. 2 Adapting to computing system evolution. 11 th European LS-DYNA Conference 2017, Salzburg, Austria
1 Overview Improving LSTC s Multifrontal Linear Solver Roger Grimes 3, Robert Lucas 3, Nick Meng 2, Francois-Henry Rouet 3, Clement Weisbecker 3, and Ting-Ting Zhu 1 1 Cray Incorporated 2 Intel Corporation
More informationWelcome to MCS 572. content and organization expectations of the course. definition and classification
Welcome to MCS 572 1 About the Course content and organization expectations of the course 2 Supercomputing definition and classification 3 Measuring Performance speedup and efficiency Amdahl s Law Gustafson
More informationECS289: Scalable Machine Learning
ECS289: Scalable Machine Learning Cho-Jui Hsieh UC Davis Oct 18, 2016 Outline One versus all/one versus one Ranking loss for multiclass/multilabel classification Scaling to millions of labels Multiclass
More informationMAA507, Power method, QR-method and sparse matrix representation.
,, and representation. February 11, 2014 Lecture 7: Overview, Today we will look at:.. If time: A look at representation and fill in. Why do we need numerical s? I think everyone have seen how time consuming
More informationCpt S 223. School of EECS, WSU
Algorithm Analysis 1 Purpose Why bother analyzing code; isn t getting it to work enough? Estimate time and memory in the average case and worst case Identify bottlenecks, i.e., where to reduce time Compare
More informationLINEAR AND NONLINEAR PROGRAMMING
LINEAR AND NONLINEAR PROGRAMMING Stephen G. Nash and Ariela Sofer George Mason University The McGraw-Hill Companies, Inc. New York St. Louis San Francisco Auckland Bogota Caracas Lisbon London Madrid Mexico
More informationCME342 Parallel Methods in Numerical Analysis. Matrix Computation: Iterative Methods II. Sparse Matrix-vector Multiplication.
CME342 Parallel Methods in Numerical Analysis Matrix Computation: Iterative Methods II Outline: CG & its parallelization. Sparse Matrix-vector Multiplication. 1 Basic iterative methods: Ax = b r = b Ax
More informationA Service Architecture for Processing Big Earth Data in the Cloud with Geospatial Analytics and Machine Learning
A Service Architecture for Processing Big Earth Data in the Cloud with Geospatial Analytics and Machine Learning WOLFGANG GLATZ & THOMAS BAHR 1 Abstract: The Geospatial Services Framework (GSF) brings
More informationTutorial on: Optimization I. (from a deep learning perspective) Jimmy Ba
Tutorial on: Optimization I (from a deep learning perspective) Jimmy Ba Outline Random search v.s. gradient descent Finding better search directions Design white-box optimization methods to improve computation
More informationScientific Computing with Case Studies SIAM Press, Lecture Notes for Unit VII Sparse Matrix
Scientific Computing with Case Studies SIAM Press, 2009 http://www.cs.umd.edu/users/oleary/sccswebpage Lecture Notes for Unit VII Sparse Matrix Computations Part 1: Direct Methods Dianne P. O Leary c 2008
More informationConsider the following example of a linear system:
LINEAR SYSTEMS Consider the following example of a linear system: Its unique solution is x + 2x 2 + 3x 3 = 5 x + x 3 = 3 3x + x 2 + 3x 3 = 3 x =, x 2 = 0, x 3 = 2 In general we want to solve n equations
More informationSTA141C: Big Data & High Performance Statistical Computing
STA141C: Big Data & High Performance Statistical Computing Lecture 8: Optimization Cho-Jui Hsieh UC Davis May 9, 2017 Optimization Numerical Optimization Numerical Optimization: min X f (X ) Can be applied
More informationMore Science per Joule: Bottleneck Computing
More Science per Joule: Bottleneck Computing Georg Hager Erlangen Regional Computing Center (RRZE) University of Erlangen-Nuremberg Germany PPAM 2013 September 9, 2013 Warsaw, Poland Motivation (1): Scalability
More informationNumerical Linear Algebra Primer. Ryan Tibshirani Convex Optimization
Numerical Linear Algebra Primer Ryan Tibshirani Convex Optimization 10-725 Consider Last time: proximal Newton method min x g(x) + h(x) where g, h convex, g twice differentiable, and h simple. Proximal
More informationScientific Matrix Factorizations in Spark at Scale
Scientific Matrix Factorizations in Spark at Scale Cross-platform performance, scaling, and comparisons with C+MPI Alex Gittens, Aditya Devarakonda, Evan Racah, Michael Ringenburg, Lisa Gerhardt, Jey Kottaalam,
More informationECS289: Scalable Machine Learning
ECS289: Scalable Machine Learning Cho-Jui Hsieh UC Davis Sept 27, 2015 Outline Linear regression Ridge regression and Lasso Time complexity (closed form solution) Iterative Solvers Regression Input: training
More informationiretilp : An efficient incremental algorithm for min-period retiming under general delay model
iretilp : An efficient incremental algorithm for min-period retiming under general delay model Debasish Das, Jia Wang and Hai Zhou EECS, Northwestern University, Evanston, IL 60201 Place and Route Group,
More informationNumerical Methods I Non-Square and Sparse Linear Systems
Numerical Methods I Non-Square and Sparse Linear Systems Aleksandar Donev Courant Institute, NYU 1 donev@courant.nyu.edu 1 MATH-GA 2011.003 / CSCI-GA 2945.003, Fall 2014 September 25th, 2014 A. Donev (Courant
More informationx x2 2 + x3 3 x4 3. Use the divided-difference method to find a polynomial of least degree that fits the values shown: (b)
Numerical Methods - PROBLEMS. The Taylor series, about the origin, for log( + x) is x x2 2 + x3 3 x4 4 + Find an upper bound on the magnitude of the truncation error on the interval x.5 when log( + x)
More informationFast, Cheap and Deep Scaling machine learning
Fast, Cheap and Deep Scaling machine learning SFW Alexander Smola CMU Machine Learning and github.com/dmlc Many thanks to Mu Li Dave Andersen Chris Dyer Li Zhou Ziqi Liu Manzil Zaheer Qicong Chen Amr Ahmed
More informationFaster Machine Learning via Low-Precision Communication & Computation. Dan Alistarh (IST Austria & ETH Zurich), Hantian Zhang (ETH Zurich)
Faster Machine Learning via Low-Precision Communication & Computation Dan Alistarh (IST Austria & ETH Zurich), Hantian Zhang (ETH Zurich) 2 How many bits do you need to represent a single number in machine
More informationARock: an algorithmic framework for asynchronous parallel coordinate updates
ARock: an algorithmic framework for asynchronous parallel coordinate updates Zhimin Peng, Yangyang Xu, Ming Yan, Wotao Yin ( UCLA Math, U.Waterloo DCO) UCLA CAM Report 15-37 ShanghaiTech SSDS 15 June 25,
More information6.4 Krylov Subspaces and Conjugate Gradients
6.4 Krylov Subspaces and Conjugate Gradients Our original equation is Ax = b. The preconditioned equation is P Ax = P b. When we write P, we never intend that an inverse will be explicitly computed. P
More informationMotivation Subgradient Method Stochastic Subgradient Method. Convex Optimization. Lecture 15 - Gradient Descent in Machine Learning
Convex Optimization Lecture 15 - Gradient Descent in Machine Learning Instructor: Yuanzhang Xiao University of Hawaii at Manoa Fall 2017 1 / 21 Today s Lecture 1 Motivation 2 Subgradient Method 3 Stochastic
More informationDot-Product Join: Scalable In-Database Linear Algebra for Big Model Analytics
Dot-Product Join: Scalable In-Database Linear Algebra for Big Model Analytics Chengjie Qin 1 and Florin Rusu 2 1 GraphSQL, Inc. 2 University of California Merced June 29, 2017 Machine Learning (ML) Is
More informationHomework 5. Convex Optimization /36-725
Homework 5 Convex Optimization 10-725/36-725 Due Tuesday November 22 at 5:30pm submitted to Christoph Dann in Gates 8013 (Remember to a submit separate writeup for each problem, with your name at the top)
More informationLecture 14: October 17
1-725/36-725: Convex Optimization Fall 218 Lecture 14: October 17 Lecturer: Lecturer: Ryan Tibshirani Scribes: Pengsheng Guo, Xian Zhou Note: LaTeX template courtesy of UC Berkeley EECS dept. Disclaimer:
More informationCPSC 540: Machine Learning
CPSC 540: Machine Learning First-Order Methods, L1-Regularization, Coordinate Descent Winter 2016 Some images from this lecture are taken from Google Image Search. Admin Room: We ll count final numbers
More informationReinforcement Learning
Reinforcement Learning Ron Parr CompSci 7 Department of Computer Science Duke University With thanks to Kris Hauser for some content RL Highlights Everybody likes to learn from experience Use ML techniques
More informationAM 205: lecture 19. Last time: Conditions for optimality Today: Newton s method for optimization, survey of optimization methods
AM 205: lecture 19 Last time: Conditions for optimality Today: Newton s method for optimization, survey of optimization methods Optimality Conditions: Equality Constrained Case As another example of equality
More informationSparse LU Factorization on GPUs for Accelerating SPICE Simulation
Nano-scale Integrated Circuit and System (NICS) Laboratory Sparse LU Factorization on GPUs for Accelerating SPICE Simulation Xiaoming Chen PhD Candidate Department of Electronic Engineering Tsinghua University,
More informationScalable machine learning for massive datasets: Fast summation algorithms
Scalable machine learning for massive datasets: Fast summation algorithms Getting good enough solutions as fast as possible Vikas Chandrakant Raykar vikas@cs.umd.edu University of Maryland, CollegePark
More informationIPAM Summer School Optimization methods for machine learning. Jorge Nocedal
IPAM Summer School 2012 Tutorial on Optimization methods for machine learning Jorge Nocedal Northwestern University Overview 1. We discuss some characteristics of optimization problems arising in deep
More informationQR Factorization of Tall and Skinny Matrices in a Grid Computing Environment
QR Factorization of Tall and Skinny Matrices in a Grid Computing Environment Emmanuel AGULLO (INRIA / LaBRI) Camille COTI (Iowa State University) Jack DONGARRA (University of Tennessee) Thomas HÉRAULT
More informationTASM: Top-k Approximate Subtree Matching
TASM: Top-k Approximate Subtree Matching Nikolaus Augsten 1 Denilson Barbosa 2 Michael Böhlen 3 Themis Palpanas 4 1 Free University of Bozen-Bolzano, Italy augsten@inf.unibz.it 2 University of Alberta,
More informationContents. 1 Introduction. 1.1 History of Optimization ALG-ML SEMINAR LISSA: LINEAR TIME SECOND-ORDER STOCHASTIC ALGORITHM FEBRUARY 23, 2016
ALG-ML SEMINAR LISSA: LINEAR TIME SECOND-ORDER STOCHASTIC ALGORITHM FEBRUARY 23, 2016 LECTURERS: NAMAN AGARWAL AND BRIAN BULLINS SCRIBE: KIRAN VODRAHALLI Contents 1 Introduction 1 1.1 History of Optimization.....................................
More informationSolving Quadratic Equations with XL on Parallel Architectures
Solving Quadratic Equations with XL on Parallel Architectures Cheng Chen-Mou 1, Chou Tung 2, Ni Ru-Ben 2, Yang Bo-Yin 2 1 National Taiwan University 2 Academia Sinica Taipei, Taiwan Leuven, Sept. 11, 2012
More informationEstimates for factoring 1024-bit integers. Thorsten Kleinjung, University of Bonn
Estimates for factoring 1024-bit integers Thorsten Kleinjung, University of Bonn Contents GNFS Overview Polynomial selection, matrix construction, square root computation Sieving and cofactoring Strategies
More informationStructured tensor missing-trace interpolation in the Hierarchical Tucker format Curt Da Silva and Felix J. Herrmann Sept. 26, 2013
Structured tensor missing-trace interpolation in the Hierarchical Tucker format Curt Da Silva and Felix J. Herrmann Sept. 6, 13 SLIM University of British Columbia Motivation 3D seismic experiments - 5D
More informationStat. 758: Computation and Programming
Stat. 758: Computation and Programming Eric B. Laber Department of Statistics, North Carolina State University Lecture 4a Sept. 10, 2015 Ambition is like a frog sitting on a Venus flytrap. The flytrap
More informationBinary Decision Diagrams and Symbolic Model Checking
Binary Decision Diagrams and Symbolic Model Checking Randy Bryant Ed Clarke Ken McMillan Allen Emerson CMU CMU Cadence U Texas http://www.cs.cmu.edu/~bryant Binary Decision Diagrams Restricted Form of
More informationNumerical Methods I: Numerical linear algebra
1/3 Numerical Methods I: Numerical linear algebra Georg Stadler Courant Institute, NYU stadler@cimsnyuedu September 1, 017 /3 We study the solution of linear systems of the form Ax = b with A R n n, x,
More informationCPSC 540: Machine Learning
CPSC 540: Machine Learning Mixture Models, Density Estimation, Factor Analysis Mark Schmidt University of British Columbia Winter 2016 Admin Assignment 2: 1 late day to hand it in now. Assignment 3: Posted,
More informationIntroduction to ArcGIS GeoAnalytics Server. Sarah Ambrose & Noah Slocum
Introduction to ArcGIS GeoAnalytics Server Sarah Ambrose & Noah Slocum Agenda Overview Analysis Capabilities + Demo Deployment and Configuration Questions ArcGIS GeoAnalytics Server uses the power of distributed
More informationECS289: Scalable Machine Learning
ECS289: Scalable Machine Learning Cho-Jui Hsieh UC Davis Oct 27, 2015 Outline One versus all/one versus one Ranking loss for multiclass/multilabel classification Scaling to millions of labels Multiclass
More informationNonlinear Optimization for Optimal Control
Nonlinear Optimization for Optimal Control Pieter Abbeel UC Berkeley EECS Many slides and figures adapted from Stephen Boyd [optional] Boyd and Vandenberghe, Convex Optimization, Chapters 9 11 [optional]
More informationProgressive & Algorithms & Systems
University of California Merced Lawrence Berkeley National Laboratory Progressive Computation for Data Exploration Progressive Computation Online Aggregation (OLA) in DB Query Result Estimate Result ε
More informationFast Multipole Methods: Fundamentals & Applications. Ramani Duraiswami Nail A. Gumerov
Fast Multipole Methods: Fundamentals & Applications Ramani Duraiswami Nail A. Gumerov Week 1. Introduction. What are multipole methods and what is this course about. Problems from physics, mathematics,
More informationHarvard Center for Geographic Analysis Geospatial on the MOC
2017 Massachusetts Open Cloud Workshop Boston University Harvard Center for Geographic Analysis Geospatial on the MOC Ben Lewis Harvard Center for Geographic Analysis Aaron Williams MapD Small Team Supporting
More informationJacobi-Based Eigenvalue Solver on GPU. Lung-Sheng Chien, NVIDIA
Jacobi-Based Eigenvalue Solver on GPU Lung-Sheng Chien, NVIDIA lchien@nvidia.com Outline Symmetric eigenvalue solver Experiment Applications Conclusions Symmetric eigenvalue solver The standard form is
More informationScalable Asynchronous Gradient Descent Optimization for Out-of-Core Models
Scalable Asynchronous Gradient Descent Optimization for Out-of-Core Models Chengjie Qin 1, Martin Torres 2, and Florin Rusu 2 1 GraphSQL, Inc. 2 University of California Merced August 31, 2017 Machine
More informationAMS526: Numerical Analysis I (Numerical Linear Algebra)
AMS526: Numerical Analysis I (Numerical Linear Algebra) Lecture 21: Sensitivity of Eigenvalues and Eigenvectors; Conjugate Gradient Method Xiangmin Jiao Stony Brook University Xiangmin Jiao Numerical Analysis
More information