English
Related papers

Related papers: Normalized Gradients for All

200 papers

Implicit layer deep learning techniques, like Neural Differential Equations, have become an important modeling framework due to their ability to adapt to new problems automatically. Training a neural differential equation is effectively a…

Machine Learning · Computer Science 2023-06-05 Avik Pal , Alan Edelman , Chris Rackauckas

Normalizing flows are a powerful technique for obtaining reparameterizable samples from complex multimodal distributions. Unfortunately, current approaches are only available for the most basic geometries and fall short when the underlying…

Machine Learning · Statistics 2021-05-03 Luca Falorsi

We study boundary regularity of viscosity solutions to fully nonlinear degenerate or singular parabolic equations. The gradient-dependent degeneracy or singularity, along with the time derivative, introduces significant challenges beyond…

Analysis of PDEs · Mathematics 2025-09-24 Hyungsung Yun

Fractional derivatives are a well-studied generalization of integer order derivatives. Naturally, for optimization, it is of interest to understand the convergence properties of gradient descent using fractional derivatives. Convergence…

Optimization and Control · Mathematics 2024-06-05 Ashwani Aggarwal

Smoothness is crucial for attaining fast rates in first-order optimization. However, many optimization problems in modern machine learning involve non-smooth objectives. Recent studies relax the smoothness assumption by allowing the…

Optimization and Control · Mathematics 2026-02-11 Dingzhi Yu , Wei Jiang , Hongyi Tao , Yuanyu Wan , Lijun Zhang

Recently there are a considerable amount of work devoted to the study of the algorithmic stability and generalization for stochastic gradient descent (SGD). However, the existing stability analysis requires to impose restrictive assumptions…

Machine Learning · Computer Science 2020-06-16 Yunwen Lei , Yiming Ying

Probabilistic smoothing is a standard tool for global optimization, but existing methods rely on Gaussian kernels and specific transforms, often resulting in strong hyperparameter sensitivity and limited robustness. We propose a general…

Machine Learning · Computer Science 2026-05-27 Kukyoung Jang , Taehyun Cho , Junrui Zhang , Ping Xu , Kyungjae Lee

In this work, we develop new optimization algorithms that use approximate second-order information combined with the gradient regularization technique to achieve fast global convergence rates for both convex and non-convex objectives. The…

Optimization and Control · Mathematics 2025-06-17 Andrei Semenov , Martin Jaggi , Nikita Doikov

In this paper we aim for a generalisation of the Steenrod Approximation Theorem from, concerning a smoothing procedure for sections in smooth locally trivial bundles. The generalisation is that we consider locally trivial smooth bundles…

Differential Geometry · Mathematics 2010-01-04 Christoph Wockel

We suggest simple implementable modifications of conditional gradient and gradient projection methods for smooth convex optimization problems in Hilbert spaces. Usually, the custom methods attain only weak convergence. We prove strong…

Optimization and Control · Mathematics 2017-05-04 Igor Konnov

This paper addresses the study of derivative-free smooth optimization problems, where the gradient information on the objective function is unavailable. Two novel general derivative-free methods are proposed and developed for minimizing…

Optimization and Control · Mathematics 2023-11-29 Pham Duy Khanh , Boris S. Mordukhovich , Dat Ba Tran

A widely believed explanation for the remarkable generalization capacities of overparameterized neural networks is that the optimization algorithms used for training induce an implicit bias towards benign solutions. To grasp this…

Machine Learning · Computer Science 2025-12-19 Maria Matveev , Vit Fojtik , Hung-Hsu Chou , Gitta Kutyniok , Johannes Maly

Normalization layers (e.g., Batch Normalization, Layer Normalization) were introduced to help with optimization difficulties in very deep nets, but they clearly also help generalization, even in not-so-deep nets. Motivated by the long-held…

Machine Learning · Computer Science 2023-01-18 Kaifeng Lyu , Zhiyuan Li , Sanjeev Arora

To improve the off-sample generalization of classical procedures minimizing the empirical risk under potentially heavy-tailed data, new robust learning algorithms have been proposed in recent years, with generalized median-of-means…

Machine Learning · Statistics 2018-10-16 Matthew J. Holland

The dependence of the smoothness of variational solutions to the first boundary value problems for second order elliptic operators are studied. The results use Sobolev-Slobodetskii and Nikolskii-Besov spaces and their properties. Methods…

Analysis of PDEs · Mathematics 2016-05-11 I. V. Tsylin

Gradient-based saliency maps are widely used to explain deep neural network decisions. However, as models become deeper and more black-box, such as in closed-source APIs like ChatGPT, computing gradients become challenging, hindering…

Computer Vision and Pattern Recognition · Computer Science 2024-07-03 Zeliang Zhang , Mingqian Feng , Jinyang Jiang , Rongyi Zhu , Yijie Peng , Chenliang Xu

An open question in the Deep Learning community is why neural networks trained with Gradient Descent generalize well on real datasets even though they are capable of fitting random data. We propose an approach to answering this question…

Machine Learning · Computer Science 2020-02-26 Satrajit Chatterjee

In this paper, we study local regularity of the solutions to the Stokes equations near a curved boundary under no-slip or Navier boundary conditions. We extend previous boundary estimates near a flat boundary to that near a curved boundary,…

Analysis of PDEs · Mathematics 2025-10-23 Hui Chen , Su Liang , Tai-Peng Tsai

How to find flat minima? We propose running normalized gradient descent, usually reserved for nonsmooth optimization, with sufficiently slowly diminishing step sizes. This induces implicit regularization towards flat minima if an…

Optimization and Control · Mathematics 2026-02-10 Cédric Josz

This work introduces a hybrid non-Euclidean optimization method which generalizes gradient norm clipping by combining steepest descent and conditional gradient approaches. The method achieves the best of both worlds by establishing a…

Machine Learning · Computer Science 2026-02-05 Thomas Pethick , Wanyun Xie , Mete Erdogan , Kimon Antonakopoulos , Antonio Silveti-Falls , Volkan Cevher