English
Related papers

Related papers: Gradient Flow Polarizes Softmax Outputs towards Lo…

200 papers

We propose DropMax, a stochastic version of softmax classifier which at each iteration drops non-target classes according to dropout probabilities adaptively decided for each instance. Specifically, we overlay binary masking variables over…

Machine Learning · Computer Science 2018-11-05 Hae Beom Lee , Juho Lee , Saehoon Kim , Eunho Yang , Sung Ju Hwang

Neural collapse (NC) describes the structured geometry that emerges in the features and weights of trained classifiers. Recent theory suggests NC can be suboptimal in deep architectures, attributing this to an explicit low-rank bias from L2…

Machine Learning · Computer Science 2026-05-25 Connall Garrod , Jonathan P. Keating , Christos Thrampoulidis

Quadratic programming is a workhorse of modern nonlinear optimization, control, and data science. Although regularized methods offer convergence guarantees under minimal assumptions on the problem data, they can exhibit the slow…

Optimization and Control · Mathematics 2026-05-18 Jeremy Bertoncini , Alberto De Marchi , Matthias Gerdts , Simon Gottschalk

Decoding in large language models is often described as scoring tokens and normalizing with softmax. We give a minimal, self-contained account of this step as a constrained variational principle on the probability simplex. The discrete,…

Machine Learning · Computer Science 2025-09-01 Christopher R. Lee-Jenkins

We examine the intrinsic (within the attention head) and extrinsic (amongst the attention heads) structure of the self-attention mechanism in transformers. Theoretical evidence for invariance of the self-attention mechanism to softmax…

Numerical Analysis · Mathematics 2025-06-19 Oluwadamilola Fasina , Ruben V. C. Pohle , Pei-Chun Su , Ronald R. Coifman

We propose a new reduced model for gravity-driven free-surface flows of shallow elastic fluids. It is obtained by an asymptotic expansion of the upper-convected Maxwell model for elastic fluids. The viscosity is assumed small (of order…

Numerical Analysis · Mathematics 2013-06-13 François Bouchut , Sébastien Boyaval

Flow-based models are powerful tools for designing probabilistic models with tractable density. This paper introduces Convex Potential Flows (CP-Flow), a natural and efficient parameterization of invertible models inspired by the optimal…

Machine Learning · Computer Science 2021-02-25 Chin-Wei Huang , Ricky T. Q. Chen , Christos Tsirigotis , Aaron Courville

We approach the problem of learning continuous normalizing flows from a dual perspective motivated by entropy-regularized optimal transport, in which continuous normalizing flows are cast as gradients of scalar potential functions. This…

Machine Learning · Computer Science 2020-06-12 Chris Finlay , Augusto Gerolin , Adam M Oberman , Aram-Alexandre Pooladian

Linear attention has attracted interest as a computationally efficient approximation to softmax attention, especially for long sequences. Recent studies have explored distilling softmax attention in pre-trained Transformers into linear…

Machine Learning · Computer Science 2025-07-08 Naoki Nishikawa , Rei Higuchi , Taiji Suzuki

Despite the success achieved by the analysis of supervised learning algorithms in the framework of statistical mechanics, reinforcement learning has remained largely untouched. Here we move towards closing the gap by analyzing the dynamics…

Statistical Mechanics · Physics 2022-09-02 Riccardo Fabbricatore , Vladimir V. Palyulin

In this paper, we combine deep learning concepts and some proper orthogonal decomposition (POD) model reduction methods for predicting flow in heterogeneous porous media. Nonlinear flow dynamics is studied, where the dynamics is regarded as…

Numerical Analysis · Mathematics 2025-09-12 Siu Wun Cheung , Eric T. Chung , Yalchin Efendiev , Eduardo Gildin , Yating Wang , Jingyan Zhang

The adversarial robustness of attributions is a fundamental requirement for reliable explainability in deep learning, yet existing approaches typically rely on computationally expensive explicit regularization. In this work, we show that…

Machine Learning · Computer Science 2026-05-29 Amir Mehrpanah , Matteo Gamba , Hossein Azizpour

We prove that the standard gradient flow in parameter space that underlies many training algorithms in deep learning can be continuously deformed into an adapted gradient flow which yields (constrained) Euclidean gradient flow in output…

Machine Learning · Computer Science 2026-02-02 Thomas Chen , Patrícia Muñoz Ewald

This paper investigates the problem of regulating in real time a linear dynamical system to the solution trajectory of a time-varying constrained convex optimization problem. The proposed feedback controller is based on an adaptation of the…

Optimization and Control · Mathematics 2021-09-13 Gianluca Bianchin , Jorge Cortes , Jorge I. Poveda , Emiliano Dall'Anese

The quadratic computation complexity of self-attention has been a persistent challenge when applying Transformer models to vision tasks. Linear attention, on the other hand, offers a much more efficient alternative with its linear…

Computer Vision and Pattern Recognition · Computer Science 2023-09-04 Dongchen Han , Xuran Pan , Yizeng Han , Shiji Song , Gao Huang

Understanding the fundamental mechanism behind the success of transformer networks is still an open problem in the deep learning literature. Although their remarkable performance has been mostly attributed to the self-attention mechanism,…

Machine Learning · Computer Science 2022-11-23 Tolga Ergen , Behnam Neyshabur , Harsh Mehta

Despite achieving state-of-the-art results in nearly all Natural Language Processing applications, fine-tuning Transformer-based language models still requires a significant amount of labeled data to work. A well known technique to reduce…

Machine Learning · Computer Science 2025-03-13 Julius Gonsior , Christian Falkenberg , Silvio Magino , Anja Reusch , Maik Thiele , Wolfgang Lehner

Bilevel optimization is a key framework in hierarchical decision-making, where one problem is embedded within the constraints of another. In this work, we propose a control-theoretic approach to solving bilevel optimization problems. Our…

Optimization and Control · Mathematics 2025-03-25 Sina Sharifi , Nazanin Abolfazli , Erfan Yazdandoost Hamedani , Mahyar Fazlyab

Explainability for Deep Learning Models is especially important for clinical applications, where decisions of automated systems have far-reaching consequences. While various post-hoc explainable methods, such as attention visualization and…

Training neural networks requires optimizing a loss function that may be highly irregular, and in particular neither convex nor smooth. Popular training algorithms are based on stochastic gradient descent with momentum (SGDM), for which…

Machine Learning · Computer Science 2026-03-17 Qinzi Zhang , Ashok Cutkosky