Heavy Ball method and Nesterov's gradient method are two kinds of accelerated versions of gradient methods that achieve optimal convergence for smooth optimization. I wonder whether there is an accelerated version of subgradient method. If no, can you give an intuition for why the acceleration does not work for non-smooth problems?
2026-03-25 05:59:45.1774418385
Existence of accelerated subgradient methods
81 Views Asked by Bumbble Comm https://math.techqa.club/user/bumbble-comm/detail At
1
There are 1 best solutions below
Related Questions in OPTIMIZATION
- Optimization - If the sum of objective functions are similar, will sum of argmax's be similar
- optimization with strict inequality of variables
- Gradient of Cost Function To Find Matrix Factorization
- Calculation of distance of a point from a curve
- Find all local maxima and minima of $x^2+y^2$ subject to the constraint $x^2+2y=6$. Does $x^2+y^2$ have a global max/min on the same constraint?
- What does it mean to dualize a constraint in the context of Lagrangian relaxation?
- Modified conjugate gradient method to minimise quadratic functional restricted to positive solutions
- Building the model for a Linear Programming Problem
- Maximize the function
- Transform LMI problem into different SDP form
Related Questions in CONVEX-OPTIMIZATION
- Optimization - If the sum of objective functions are similar, will sum of argmax's be similar
- Least Absolute Deviation (LAD) Line Fitting / Regression
- Check if $\phi$ is convex
- Transform LMI problem into different SDP form
- Can a linear matrix inequality constraint transform to second-order cone constraint(s)?
- Optimality conditions - necessary vs sufficient
- Minimization of a convex quadratic form
- Prove that the objective function of K-means is non convex
- How to solve a linear program without any given data?
- Distance between a point $x \in \mathbb R^2$ and $x_1^2+x_2^2 \le 4$
Related Questions in SUBGRADIENT
- how to prove the affine composition of the subdifferential?
- why subgradient of convex function is unique
- Subgradients of parametrized LP
- How to show $\partial f(x) =\{\nabla f(x) \}$ for a convex differentiable function?
- What is the subdifferential of the $f(x)$?
- Plot and calculate subgradient of f(x)
- Calculate the convex conjugate of f(x)?
- Proving necessity of a condition for minimum of a convex function
- An optimality condition for constrained problems using subgradients
- A necessary and sufficient condition for optimality of non-smooth convex functions over convex set
Related Questions in NON-SMOOTH-OPTIMIZATION
- Second order necessary and sufficient conditions for convex nonsmooth optimization
- Uses of nonsmooth analysis in mathematical research
- Optimization with parametric constraints: solution maps
- Formulate the solution of a zero sum game with a payoff matrix A as an optimization problem.
- Minimizing a composite non-differentiable convex function over a $2$-norm ball
- How to avoid overflow when evaluating the exponential smoothing function?
- Sub-differential of a convex function along a particular direction
- Optimality check for non-differentiable convex function
- Maximum of pseudoconvex function
- Example of empty Clarke subdifferential for function lipschitz over a closed convex set
Trending Questions
- Induction on the number of equations
- How to convince a math teacher of this simple and obvious fact?
- Find $E[XY|Y+Z=1 ]$
- Refuting the Anti-Cantor Cranks
- What are imaginary numbers?
- Determine the adjoint of $\tilde Q(x)$ for $\tilde Q(x)u:=(Qu)(x)$ where $Q:U→L^2(Ω,ℝ^d$ is a Hilbert-Schmidt operator and $U$ is a Hilbert space
- Why does this innovative method of subtraction from a third grader always work?
- How do we know that the number $1$ is not equal to the number $-1$?
- What are the Implications of having VΩ as a model for a theory?
- Defining a Galois Field based on primitive element versus polynomial?
- Can't find the relationship between two columns of numbers. Please Help
- Is computer science a branch of mathematics?
- Is there a bijection of $\mathbb{R}^n$ with itself such that the forward map is connected but the inverse is not?
- Identification of a quadrilateral as a trapezoid, rectangle, or square
- Generator of inertia group in function field extension
Popular # Hahtags
second-order-logic
numerical-methods
puzzle
logic
probability
number-theory
winding-number
real-analysis
integration
calculus
complex-analysis
sequences-and-series
proof-writing
set-theory
functions
homotopy-theory
elementary-number-theory
ordinary-differential-equations
circles
derivatives
game-theory
definite-integrals
elementary-set-theory
limits
multivariable-calculus
geometry
algebraic-number-theory
proof-verification
partial-derivative
algebra-precalculus
Popular Questions
- What is the integral of 1/x?
- How many squares actually ARE in this picture? Is this a trick question with no right answer?
- Is a matrix multiplied with its transpose something special?
- What is the difference between independent and mutually exclusive events?
- Visually stunning math concepts which are easy to explain
- taylor series of $\ln(1+x)$?
- How to tell if a set of vectors spans a space?
- Calculus question taking derivative to find horizontal tangent line
- How to determine if a function is one-to-one?
- Determine if vectors are linearly independent
- What does it mean to have a determinant equal to zero?
- Is this Batman equation for real?
- How to find perpendicular vector to another vector?
- How to find mean and median from histogram
- How many sides does a circle have?
The text Accelerated Methods for the SOCP-relaxed Component-based Distributed Optimal Power Flow talk about a particular problem with an accelerated subgradient method.
Perhaps you can find another texts searching, with some math expression, to accelerated subgradient method on SearchOnMath.