English
Related papers

Related papers: One-step differentiation of iterative algorithms

200 papers

This study proposes a Newton based multiple objective optimization algorithm for hyperparameter search. The first order differential (gradient) is calculated using finite difference method and a gradient matrix with vectorization is formed…

Optimization and Control · Mathematics 2024-01-09 Qinwu Xu

Bilevel Optimization Programming is used to model complex and conflicting interactions between agents, for example in Robust AI or Privacy-preserving AI. Integrating bilevel mathematical programming within deep learning is thus an essential…

Machine Learning · Computer Science 2023-03-01 Francesco Alesiani

This report considers linear multistep methods through time filtering. The approach has several advantages. It is modular and requires the addition of only one line of additional code. Error estimation and variable timesteps is…

Numerical Analysis · Mathematics 2017-08-22 Ahmet Guzel , William Layton

In multi-level systems, the commonly used adiabatic elimination is a method for approximating the dynamics of the system by eliminating irrelevant, non-resonantly coupled levels. This procedure is, however, somewhat ambiguous and it is not…

Quantum Physics · Physics 2014-05-23 Vanessa Paulisch , Rui Han , Hui Khoon Ng , Berthold-Georg Englert

The essential difficulty of gradient-based bilevel optimization using implicit differentiation is to estimate the inverse Hessian vector product with respect to neural network parameters. This paper proposes to tackle this problem by the…

Machine Learning · Computer Science 2023-02-21 Ryuichiro Hataya , Makoto Yamada

We show that the optimal complexity of Nesterov's smooth first-order optimization algorithm is preserved when the gradient is only computed up to a small, uniformly bounded error. In applications of this method to semidefinite programs,…

Optimization and Control · Mathematics 2008-05-16 Alexandre d'Aspremont

Backpropagation algorithm is indispensable for the training of feedforward neural networks. It requires propagating error gradients sequentially from the output layer all the way back to the input layer. The backward locking in…

Machine Learning · Computer Science 2018-07-24 Zhouyuan Huo , Bin Gu , Qian Yang , Heng Huang

We propose an optimization proxy in terms of iterative implicit gradient methods for solving constrained optimization problems with nonconvex loss functions. This framework can be applied to a broad range of machine learning settings,…

Optimization and Control · Mathematics 2025-10-14 Harshal D. Kaushik , Ming Jin

This work establishes new convergence guarantees for gradient descent in smooth convex optimization via a computer-assisted analysis technique. Our theory allows nonconstant stepsize policies with frequent long steps potentially violating…

Optimization and Control · Mathematics 2024-02-06 Benjamin Grimmer

Numerous Optimization Algorithms have a time-varying update rule thanks to, for instance, a changing step size, momentum parameter or, Hessian approximation. In this paper, we apply unrolled or automatic differentiation to a time-varying…

Optimization and Control · Mathematics 2024-10-28 Sheheryar Mehmood , Peter Ochs

Uncertainty quantification for deep learning is a challenging open problem. Bayesian statistics offer a mathematically grounded framework to reason about uncertainties; however, approximate posteriors for modern neural networks still…

Machine Learning · Statistics 2020-01-23 Nicolas Brosse , Carlos Riquelme , Alice Martin , Sylvain Gelly , Éric Moulines

Iterative refinement -- start with a random guess, then iteratively improve the guess -- is a useful paradigm for representation learning because it offers a way to break symmetries among equally plausible explanations for the data. This…

Machine Learning · Computer Science 2023-01-03 Michael Chang , Thomas L. Griffiths , Sergey Levine

Backpropagation's main limitation is its need to store intermediate activations (residuals) during the forward pass, which restricts the depth of trainable networks. This raises a fundamental question: can we avoid storing these…

Machine Learning · Computer Science 2026-05-25 Dmitrii Krylov , Armin Karamzade , Roy Fox

Bilevel optimization has arisen as a powerful tool in modern machine learning. However, due to the nested structure of bilevel optimization, even gradient-based methods require second-order derivative approximations via Jacobian- or/and…

Machine Learning · Computer Science 2022-06-07 Daouda Sow , Kaiyi Ji , Yingbin Liang

Automatic differentiation---the mechanical transformation of numeric computer programs to calculate derivatives efficiently and accurately---dates to the origin of the computer age. Reverse mode automatic differentiation both antedates and…

Machine Learning · Computer Science 2014-04-30 Atilim Gunes Baydin , Barak A. Pearlmutter

The scalability of continuous normalizing flows (CNFs) for unbiased Boltzmann sampling remains limited in high-dimensional systems due to the cost of Jacobian-determinant evaluation, which requires $D$ backpropagation passes through the…

Machine Learning · Computer Science 2026-01-30 Xin Peng , Ang Gao

Distributed systems have been widely used in practice to accomplish data analysis tasks of huge scales. In this work, we target on the estimation problem of generalized linear models on a distributed system with nonrandomly distributed…

Methodology · Statistics 2020-04-07 Feifei Wang , Danyang Huang , Yingqiu Zhu , Hansheng Wang

Ou et al. (2022) introduce the problem of learning set functions from data generated by a so-called optimal subset oracle. Their approach approximates the underlying utility function with an energy-based model, whose parameters are…

Machine Learning · Computer Science 2024-12-18 Gözde Özcan , Chengzhi Shi , Stratis Ioannidis

In this paper, we develop zeroth-order algorithms with provably (nearly) optimal sample complexity for stochastic bilevel optimization, where only noisy function evaluations are available. We propose two distinct algorithms: the first is…

Optimization and Control · Mathematics 2025-10-07 Alireza Aghasi , Jeongyeol Kwon , Saeed Ghadimi

The complex-step derivative approximation is a numerical differentiation technique that can achieve analytical accuracy, to machine precision, with a single function evaluation. In this letter, the complex-step derivative approximation is…

Robotics · Computer Science 2021-05-07 Charles Champagne Cossette , Alex Walsh , James Richard Forbes