20 results for “differentiable optimizer”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
The paper presents a compiler that translates Scheme into differentiable computation graphs, enabling the use of code as a learnable scientific model.
This paper reviews models of inexact computational oracles in smooth continuous optimization and their implications for optimization algorithms.
This paper proposes a new functional gradient descent algorithm that adapts the representation of functional gradients over the course of optimization, providing convergence guarantees and outperformi…
The paper provides a finite-time analysis of the Adam optimizer for nonsmooth nonconvex optimization, proving a convergence rate of $1/T^{2/13}$ with a randomly scaled learning rate.
This paper introduces a general model of genetic algorithms and studies their optimization problems using reinforcement learning.
The paper introduces Singularity-aware Adam (S-Adam), a novel optimizer that stabilizes deep learning training in non-smooth loss landscapes by dynamically damping updates based on local geometric ins…
Johanna Menn, Miriam Kober, Paul Brunzema, David Stenger +1 more
The paper introduces local Preferential Bayesian Optimization (PBO) methods that adapt high-dimensional Bayesian Optimization techniques, such as trust-region and derivative-informed local search, to…
This paper proposes new methods for bilevel optimization in machine learning tasks.
This paper shows that stochastic nonconvex optimization can be reduced to ordinary static regret minimization in online convex optimization, and establishes convergence rates for smooth and Lipschitz…
The paper proposes an inexact gradient method, PPI-GD, that improves the oracle complexity of gradient descent for smooth loss functions.
Jian Yao, Zhiyao Zhang, Yichen Li, Xingyu Wu +1 more
This paper introduces Algorithm Modelization, a paradigm that turns iterative algorithms into trainable models.
This paper investigates the benefits of generating multiple solutions in each generation for Evolutionary Diversity Optimisation (EDO) and proposes efficient methods to achieve it.
Pekka Malo, Lauri Viitasaari, Patrik Nummi, Antti Suominen +2 more
The paper introduces an operator calculus for population-based optimization methods, establishing a modular Lyapunov principle for their convergence analysis.
Cheng-Han Huang, Yongliang Sun, Chaoyan Huang, Ismail Alkhouri +1 more
The paper establishes conditions for QUBO formulations of combinatorial optimization problems that guarantee valid binary and feasible local minimizers using gradient-based methods.
This paper compares the effect of different initialization methods on the accuracy and complexity of solutions in genetic programming for symbolic regression, finding no significant differences.
A new algorithm is proposed for approximating solutions to linear-multi-parametric optimization problems with negative parameter dependencies and non-fixed parameter sets.
The paper presents TROPT, an open-source framework that unifies discrete optimizers' execution and standardizes their development under a single interface.
The paper improves the optimization problem at the core of the laser method for obtaining matrix multiplication bounds, yielding a new upper bound of ω < 2.371177.