English
Related papers

Related papers: Learning to Optimize by Differentiable Programming

200 papers

Multi-material design optimization problems can, after discretization, be solved by the iterative solution of simpler sub-problems which approximate the original problem at an expansion point to first order. In particular, models…

Numerical Analysis · Mathematics 2026-04-01 Peter Gangl , Nico Nees , Michael Stingl

Parallelization is a popular strategy for improving the performance of iterative algorithms. Optimization methods are no exception: design of efficient parallel optimization methods and tight analysis of their theoretical properties are…

Optimization and Control · Mathematics 2023-11-28 Alexander Tyurin , Peter Richtárik

Differentiable programming, enabled by automatic differentiation (AD), provides a robust framework for gradient-based optimization in computational plasma physics. While optimization is often only used towards design, we demonstrate that it…

Plasma Physics · Physics 2026-03-13 A. S. Joglekar , A. G. R. Thomas , A. L. Milder , K. G. Miller , J. P. Palastro , D. H. Froula

Deep learning models are yielding increasingly better performances thanks to multiple factors. To be successful, model may have large number of parameters or complex architectures and be trained on large dataset. This leads to large…

Machine Learning · Computer Science 2022-12-20 Jean-Roch Vlimant , Junqi Yin

We consider learning of submodular functions from data. These functions are important in machine learning and have a wide range of applications, e.g. data summarization, feature selection and active learning. Despite their combinatorial…

Machine Learning · Statistics 2018-06-18 Sebastian Tschiatschek , Aytunc Sahin , Andreas Krause

We consider Lagrangian duality based approaches to design and analyze algorithms for online energy-efficient scheduling. First, we present a primal-dual framework. Our approach makes use of the Lagrangian weak duality and convexity to…

Data Structures and Algorithms · Computer Science 2014-08-06 Nguyen Kim Thang

Distributed optimization algorithms are widely used in many industrial machine learning applications. However choosing the appropriate algorithm and cluster size is often difficult for users as the performance and convergence rate of…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-02-21 Xinghao Pan , Shivaram Venkataraman , Zizheng Tai , Joseph Gonzalez

Many real-world combinatorial problems involve uncertain parameters, which can be predicted given contextual features and historical data. These `predict-then-optimize' or `contextual optimization' problems have gained significant…

Machine Learning · Computer Science 2026-05-19 Noah Schutte , Senne Berden , Tias Guns , Krzysztof Postek , Neil Yorke-Smith

Pipeline parallelism (PP) has become a standard technique for scaling large language model (LLM) training across multiple devices. However, despite recent progress in reducing memory consumption through activation offloading, existing…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-10-08 Hongpei Li , Han Zhang , Huikang Liu , Dongdong Ge , Yinyu Ye

Optimization is central to both modern machine learning (ML) and scientific machine learning (SciML), yet the structure of the underlying optimization problems differs substantially across these domains. Classical ML typically relies on…

Numerical Analysis · Mathematics 2026-01-16 Alena Kopaničáková , Elisa Riccietti

Given the ubiquity of multi-task in practical systems, Multi-Task Learning (MTL) has found widespread application across diverse domains. In real-world scenarios, these tasks often have different priorities. For instance, In web search,…

Machine Learning · Computer Science 2024-12-17 Zhengxing Cheng , Yuheng Huang , Zhixuan Zhang , Dan Ou , Qingwen Liu

This paper develops a Pontryagin Differentiable Programming (PDP) methodology, which establishes a unified framework to solve a broad class of learning and control tasks. The PDP distinguishes from existing methods by two novel techniques:…

Machine Learning · Computer Science 2021-01-13 Wanxin Jin , Zhaoran Wang , Zhuoran Yang , Shaoshuai Mou

Deep learning optimizers are often motivated through a mix of convex and approximate second-order theory. We select three such methods -- Adam, Shampoo and Prodigy -- and argue that each method can instead be understood as a squarely…

Machine Learning · Computer Science 2024-12-09 Jeremy Bernstein , Laker Newhouse

We introduce a novel kernel-based framework for learning differential equations and their solution maps that is efficient in data requirements, in terms of solution examples and amount of measurements from each example, and computational…

Machine Learning · Statistics 2025-04-07 Yasamin Jalalian , Juan Felipe Osorio Ramirez , Alexander Hsu , Bamdad Hosseini , Houman Owhadi

Adaptive gradient-based optimizers such as Adagrad and Adam are crucial for achieving state-of-the-art performance in machine translation and language modeling. However, these methods maintain second-order statistics for each parameter,…

Machine Learning · Computer Science 2019-09-13 Rohan Anil , Vineet Gupta , Tomer Koren , Yoram Singer

We present a practical and powerful new framework for both unconstrained and constrained submodular function optimization based on discrete semidifferentials (sub- and super-differentials). The resulting algorithms, which repeatedly compute…

Data Structures and Algorithms · Computer Science 2013-08-13 Rishabh Iyer , Stefanie Jegelka , Jeff Bilmes

Optimization methods play a central role in signal processing, serving as the mathematical foundation for inference, estimation, and control. While classical iterative optimization algorithms provide interpretability and theoretical…

Machine Learning · Computer Science 2026-04-01 Nir Shlezinger , Santiago Segarra , Yi Zhang , Dvir Avrahami , Zohar Davidov , Tirza Routtenberg , Yonina C. Eldar

We introduce a machine-learning framework to learn the hyperparameter sequence of first-order methods (e.g., the step sizes in gradient descent) to quickly solve parametric convex optimization problems. Our computational architecture…

Optimization and Control · Mathematics 2024-12-23 Rajiv Sambharya , Bartolomeo Stellato

Machine learning frameworks adopt iterative optimizers to train neural networks. Conventional eager execution separates the updating of trainable parameters from forward and backward computations. However, this approach introduces…

Machine Learning · Computer Science 2021-04-02 Zixuan Jiang , Jiaqi Gu , Mingjie Liu , Keren Zhu , David Z. Pan

We present a differentiable, decision-oriented learning framework for cost prediction in a class of multi-robot decision-making problems, in which the robots need to trade off the task performance with the costs of taking actions when they…

Robotics · Computer Science 2024-03-27 Guangyao Shi , Chak Lam Shek , Nare Karapetyan , Pratap Tokekar