From Linear to Linearizable Optimization: A Novel Framework with Applications to Stationary and Non-stationary DR-submodular Optimization
- URL: http://arxiv.org/abs/2405.00065v2
- Date: Tue, 14 May 2024 00:26:29 GMT
- Title: From Linear to Linearizable Optimization: A Novel Framework with Applications to Stationary and Non-stationary DR-submodular Optimization
- Authors: Mohammad Pedramfar, Vaneet Aggarwal,
- Abstract summary: This paper introduces the notion of linearizable/quadratizable functions, a class that extends concavity and DR-submodularity.
A general meta-algorithm is used to convert concave/quadratic functions into upper quadratizable functions.
New algorithms are derived using existing results as base for convex optimization.
- Score: 33.38582292895673
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This paper introduces the notion of upper linearizable/quadratizable functions, a class that extends concavity and DR-submodularity in various settings, including monotone and non-monotone cases over different convex sets. A general meta-algorithm is devised to convert algorithms for linear/quadratic maximization into ones that optimize upper quadratizable functions, offering a unified approach to tackling concave and DR-submodular optimization problems. The paper extends these results to multiple feedback settings, facilitating conversions between semi-bandit/first-order feedback and bandit/zeroth-order feedback, as well as between first/zeroth-order feedback and semi-bandit/bandit feedback. Leveraging this framework, new algorithms are derived using existing results as base algorithms for convex optimization, improving upon state-of-the-art results in various cases. Dynamic and adaptive regret guarantees are obtained for DR-submodular maximization, marking the first algorithms to achieve such guarantees in these settings. Notably, the paper achieves these advancements with fewer assumptions compared to existing state-of-the-art results, underscoring its broad applicability and theoretical contributions to non-convex optimization.
Related papers
- Unified Projection-Free Algorithms for Adversarial DR-Submodular Optimization [28.598226670015315]
This paper introduces unified projection-free Frank-Wolfe type algorithms for adversarial DR-submodular optimization.
For every problem considered in the non-monotone setting, the proposed algorithms are either the first with proven sub-linear $alpha$-regret bounds or have better $alpha$-regret bounds than the state of the art.
arXiv Detail & Related papers (2024-03-15T07:05:44Z) - Analyzing and Enhancing the Backward-Pass Convergence of Unrolled
Optimization [50.38518771642365]
The integration of constrained optimization models as components in deep networks has led to promising advances on many specialized learning tasks.
A central challenge in this setting is backpropagation through the solution of an optimization problem, which often lacks a closed form.
This paper provides theoretical insights into the backward pass of unrolled optimization, showing that it is equivalent to the solution of a linear system by a particular iterative method.
A system called Folded Optimization is proposed to construct more efficient backpropagation rules from unrolled solver implementations.
arXiv Detail & Related papers (2023-12-28T23:15:18Z) - Optimal Algorithms for Stochastic Bilevel Optimization under Relaxed
Smoothness Conditions [9.518010235273785]
We present a novel fully Liploop Hessian-inversion-free algorithmic framework for bilevel optimization.
We show that by a slight modification of our approach our approach can handle a more general multi-objective robust bilevel optimization problem.
arXiv Detail & Related papers (2023-06-21T07:32:29Z) - Online Dynamic Submodular Optimization [0.0]
We propose new algorithms with provable performance for online binary optimization.
We numerically test our algorithms in two power system applications: fast-timescale demand response and real-time distribution network reconfiguration.
arXiv Detail & Related papers (2023-06-19T10:37:15Z) - Faster Margin Maximization Rates for Generic and Adversarially Robust Optimization Methods [20.118513136686452]
First-order optimization methods tend to inherently favor certain solutions over others when minimizing an underdetermined training objective.
We present a series of state-of-the-art implicit bias rates for mirror descent and steepest descent algorithms.
Our accelerated rates are derived by leveraging the regret bounds of online learning algorithms within this game framework.
arXiv Detail & Related papers (2023-05-27T18:16:56Z) - Linearization Algorithms for Fully Composite Optimization [61.20539085730636]
This paper studies first-order algorithms for solving fully composite optimization problems convex compact sets.
We leverage the structure of the objective by handling differentiable and non-differentiable separately, linearizing only the smooth parts.
arXiv Detail & Related papers (2023-02-24T18:41:48Z) - Accelerated First-Order Optimization under Nonlinear Constraints [73.2273449996098]
We exploit between first-order algorithms for constrained optimization and non-smooth systems to design a new class of accelerated first-order algorithms.
An important property of these algorithms is that constraints are expressed in terms of velocities instead of sparse variables.
arXiv Detail & Related papers (2023-02-01T08:50:48Z) - On Constraints in First-Order Optimization: A View from Non-Smooth
Dynamical Systems [99.59934203759754]
We introduce a class of first-order methods for smooth constrained optimization.
Two distinctive features of our approach are that projections or optimizations over the entire feasible set are avoided.
The resulting algorithmic procedure is simple to implement even when constraints are nonlinear.
arXiv Detail & Related papers (2021-07-17T11:45:13Z) - Primal-Dual Sequential Subspace Optimization for Saddle-point Problems [3.9582154141918964]
We introduce a new sequential subspace optimization method for large-scale saddle-point problems.
It solves auxiliary saddle-point problems in low-dimensional subspaces, spanned by directions derived from first-order information over the primal emphand dual variables.
Experimental results demonstrate significantly better convergence relative to popular first-order methods.
arXiv Detail & Related papers (2020-08-20T18:19:19Z) - Convergence of adaptive algorithms for weakly convex constrained
optimization [59.36386973876765]
We prove the $mathcaltilde O(t-1/4)$ rate of convergence for the norm of the gradient of Moreau envelope.
Our analysis works with mini-batch size of $1$, constant first and second order moment parameters, and possibly smooth optimization domains.
arXiv Detail & Related papers (2020-06-11T17:43:19Z) - Effective Dimension Adaptive Sketching Methods for Faster Regularized
Least-Squares Optimization [56.05635751529922]
We propose a new randomized algorithm for solving L2-regularized least-squares problems based on sketching.
We consider two of the most popular random embeddings, namely, Gaussian embeddings and the Subsampled Randomized Hadamard Transform (SRHT)
arXiv Detail & Related papers (2020-06-10T15:00:09Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.