A Numerical Analysis Approach to Convex Optimization Richard
- Slides: 52
A Numerical Analysis Approach to Convex Optimization Richard Peng
Optimization
Convex Optimization
Convex Optimization Poly-time convex optimization led to: • Approximation algorithms • Sparse recovery • Support vector machines
Interior Point Methods
Interior Point Methods
Interior Point Methods
Lighter Weight Tools: • • • (Stochastic) (Accelerated) (gradient / mirror / coordinate) descent Alternating direction method of multipliers (ADMM) Regret minimization / MWU
Why High Accuracy Solvers?
This Talk New high accuracy algorithms for large classes of convex objectives • Faster convergence, • Better overall runtime, • Simpler algorithms
Outline
p = ∞ Linear programming
p = ∞ Linear programming
p = ∞ Linear programming
p = ∞ Linear programming
Geometric View https: //www. monroecc. edu/faculty/paulseeburger/calcnsf/Calc. Plot 3 D/
p = 1: sparse recovery
Other values of p Widely used due to availability of gradients (for back-propagation): • [El. Alaoui-Cheng-Ramdas. Wainwright-Jordan COLT 16]: p-norm regularization • [Ibrahami-Gleich WWW `19]: 1. 5&3 -norm diffusion for semi-supervised learning
On graphs p 1 2 ∞ Shortest Path Electrical flow Max-flow Min-cut Spring-mass system Negative cycle detection edge-vertex incidence matrix Beu = -1/1 for endpoints u 0 everywhere else
Norms & Algorithms • Gaussian distributions arise naturally, but were the method of choice for modeling because [Gauss 1809] came with efficient algorithms • Laplace distributions now much more common in machine learning, signal processing, privacy…
[BCLL, STOC `18] [NN’ 94] a [BCLL ’ 18] p
[AKPS, SODA `19] [NN’ 94] a [BCLL ’ 18] [AKPS `19] p
[AKPS, SODA `19] [NN’ 94] a [BCLL ’ 18] [AKPS `19] p
On graphs, using more graphs m 1. 5 [LS `19]: m 11/8+o(1) via p = O(log 1/2 n) in inner loop runtime m 1. 33 m 1 2 value of p 4 ∞
Outline
Quadratic minimization solving a system of linear equations • Gaussian elimination / exact method • Iterative / numerical methods
Quadratic minimization solving a system of linear equations • Gaussian elimination / exact method • Iterative / numerical methods Build upon these, since we’re looking for iterative convergence
Inner Loop Problem
Ideal Algorithm: %s/2/p Replace all 2 s by ps: Solve p-norm regression to high accuracy by solving a sequence of p-norm regression problems, each to low accuracy •
Replace 2 s by 4 s?
Replace 2 s by 4 s?
Outline
Replace 2 s by ps, but keep the 2 s
Replace 2 s by ps, but keep the 2 s Key difference: add back the quadratic term
Issue replacing 2 s by 4 s? ≈ Can study this issue entry-wise
Sufficient Condition Bregman Divergence: contribution of higher (2 nd after) order terms = Integral over 2 nd order derivative Sufficient and necessary: problem in inner loop approximates the Bregman Divergence
Fix: add back the 2 nd order terms
Fixed algorithm
Proof
Proof
Proof lower bound upper bound ≤ 11 × lower bound exact Bregman divergence
Outline
Iterative Reweighted Least Squares
[APS Neurips `19]: Provable IRLS
[APS Neurips `19] IRLS vs. CVX
Summary [NN’ 94] a [BCLL ’ 18] [AKPS `19] p
- Concave vs convex shapes
- Convex hull is the smallest convex set
- Convex optimization in machine learning javatpoint
- Exact matrix completion via convex optimization
- Convex optimization
- Numerical optimization techniques for engineering design
- Looking for richard stream
- Graphical method numerical analysis
- Definition of interpolation in numerical analysis
- Numerical analysis formula
- Central difference interpolation formula
- Types of errors in numerical methods
- Stirling's formula in numerical methods
- Difference between secant and false position method
- C programming and numerical analysis an introduction
- Trapezoidal sum
- Numerical analysis
- Linear optimization and prescriptive analysis
- Network configuration optimization analysis
- Virtual and datagram networks
- Theoretical models of counseling
- Waterfall and sprinkler strategy
- Approach approach conflict
- Cognitive approach vs behavioral approach
- Research design definition
- Traditional approach vs object oriented approach
- Tony wagner's seven survival skills
- The discus thrower by richard selzer explanation
- Button button plot diagram
- Pigeons poem by richard kell analysis
- Weld symbols examples
- Convex limacon
- Converging lines diagram
- Polygons definition
- Convex and concave polygons
- Arie triunghi isoscel
- Sherin stanley
- Convex vs concave teeth
- Mirror equation
- Concave vs convex light refraction
- Concave mirror salt
- Emetropy
- Concave convex lens simulation
- Traction of joints
- Slope of an indifference curve
- Property of converging lens
- Graph the curve. r = 3 + sin(4?)
- Convex heptagon
- Capitulo trochlear groove
- Fresnel and fraunhofer difference
- Convex profile
- Graham scan
- Converging lens in water