English
Related papers

Related papers: Optimizer-Induced Mode Connectivity: From AdamW to…

200 papers

Atomistic foundation models constitute a paradigm shift in computational materials science by providing universal machine-learned interatomic potentials with broad transferability across chemical spaces. Although fine-tuning is essential…

Computational Physics · Physics 2025-12-08 Xiaoqing Liu , Yangshuai Wang , Teng Zhao

We study the implicit regularization of optimization methods for linear models interpolating the training data in the under-parametrized and over-parametrized regimes. Since it is difficult to determine whether an optimizer converges to…

Machine Learning · Computer Science 2022-07-12 Sharan Vaswani , Reza Babanezhad , Jose Gallego-Posada , Aaron Mishkin , Simon Lacoste-Julien , Nicolas Le Roux

The optimization of large language models (LLMs) remains a critical challenge, particularly as model scaling exacerbates sensitivity to algorithmic imprecision and training instability. Recent advances in optimizers have improved…

Machine Learning · Computer Science 2025-11-26 Wei He , Kai Han , Hang Zhou , Hanting Chen , Zhicheng Liu , Xinghao Chen , Yunhe Wang

Understanding generalization of overparametrized neural networks remains a fundamental challenge in machine learning. Most of the literature mostly studies generalization from an interpolation point of view, taking convergence of parameters…

Machine Learning · Computer Science 2025-06-13 Etienne Boursier , Nicolas Flammarion

Implicit neural networks have become increasingly attractive in the machine learning community since they can achieve competitive performance but use much less computational resources. Recently, a line of theoretical works established the…

Machine Learning · Computer Science 2022-10-03 Tianxiang Gao , Hongyang Gao

Mode connectivity is a surprising phenomenon in the loss landscape of deep nets. Optima -- at least those discovered by gradient-based optimization -- turn out to be connected by simple paths on which the loss function is almost constant.…

Machine Learning · Computer Science 2020-01-07 Rohith Kuditipudi , Xiang Wang , Holden Lee , Yi Zhang , Zhiyuan Li , Wei Hu , Sanjeev Arora , Rong Ge

The problem of linking functional connectomics to behavior is extremely challenging due to the complex interactions between the two distinct, but related, data domains. We propose a coupled manifold optimization framework which projects…

Machine Learning · Computer Science 2020-07-07 Niharika Shimona D'Souza , Mary Beth Nebel , Nicholas Wymbs , Stewart Mostofsky , Archana Venkataraman

Deep networks with continuous piecewise affine activations induce polyhedral partitions of the input space, making the number of realized affine regions a natural measure of expressive capacity and a key determinant of how well the model…

Machine Learning · Computer Science 2026-05-12 Yi Wei , Xuan Qi , Furao Shen

We argue that the optimization plays a crucial role in generalization of deep learning models through implicit regularization. We do this by demonstrating that generalization ability is not controlled by network size but rather by some…

Machine Learning · Computer Science 2017-05-10 Behnam Neyshabur , Ryota Tomioka , Ruslan Salakhutdinov , Nathan Srebro

Modern optimizers, like Muon, impose matrix-wise geometry constraints on their updates. These matrix-wise constraints can be unified under Linear Minimization Oracle (LMO) theory. However, all current methods impose fixed LMO geometries for…

Artificial Intelligence · Computer Science 2026-05-20 Thomas Massena , Corentin Friedrich , Mathieu Serrurier

Due to the nonlinear nature of Deep Neural Networks (DNNs), one can not guarantee convergence to a unique global minimum of the loss when using optimizers relying only on local information, such as SGD. Indeed, this was a primary source of…

We study optimization problems where the objective function is modeled through feedforward neural networks with rectified linear unit (ReLU) activation. Recent literature has explored the use of a single neural network to model either…

Machine Learning · Computer Science 2022-05-11 Keliang Wang , Leonardo Lozano , Carlos Cardonha , David Bergman

The recently introduced optimizer, Muon, has gained increasing attention due to its superior performance across a wide range of applications. However, its effectiveness in federated learning remains unexplored. To address this gap, this…

Machine Learning · Computer Science 2025-10-07 Xinwen Zhang , Hongchang Gao

Muon, a recently proposed optimizer that leverages the inherent matrix structure of neural network parameters, has demonstrated strong empirical performance, indicating its potential as a successor to standard optimizers such as AdamW. This…

Machine Learning · Computer Science 2025-11-24 Naoki Sato , Hiroki Naganuma , Hideaki Iiduka

We consider the embedding of piecewise-linear deep neural networks (ReLU networks) as surrogate models in mixed-integer linear programming (MILP) problems. A MILP formulation of ReLU networks has recently been applied by many authors to…

Optimization and Control · Mathematics 2022-01-10 Bjarne Grimstad , Henrik Andersson

Muon is a matrix-aware optimizer that leverages Newton-Schulz (NS) iterations to enforce spectral gradient orthogonalization by driving all singular values of the momentum matrix toward 1. While this uniform spectral whitening enhances…

Machine Learning · Computer Science 2026-05-20 Chongyu Fan , Gaowen Liu , Mingyi Hong , Ramana Rao Kompella , Sijia Liu

Trained ML models are commonly embedded in optimization problems. In many cases, this leads to large-scale NLPs that are difficult to solve to global optimality. While ML models frequently lead to large problems, they also exhibit…

Optimization and Control · Mathematics 2024-01-17 Artur M. Schweidtmann , Dominik Bongartz , Alexander Mitsos

ReLU neural networks trained as surrogate models can be embedded exactly in mixed-integer linear programs (MILPs), enabling global optimization over the learned function. The tractability of the resulting MILP depends on structural…

Optimization and Control · Mathematics 2026-04-27 Calvin Tsay

This work presents a novel, fully Riemannian framework for Low-Rank Adaptation (LoRA) that geometrically treats low-rank adapters by optimizing them directly on the fixed-rank manifold. This formulation eliminates the parametrization…

As optimizers are critical to the performances of neural networks, every year a large number of papers innovating on the subject are published. However, while most of these publications provide incremental improvements to existing…

Machine Learning · Computer Science 2021-08-10 Less Wright , Nestor Demeure
‹ Prev 1 3 4 5 6 7 10 Next ›