English
Related papers

Related papers: Flatness After All?

200 papers

Modern deep learning models are over-parameterized, where different optima can result in widely varying generalization performance. The Sharpness-Aware Minimization (SAM) technique modifies the fundamental loss function that steers gradient…

Generalization remains a critical challenge in speech deepfake detection (SDD). While various approaches aim to improve robustness, generalization is typically assessed through performance metrics like equal error rate without a theoretical…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-16 Wen Huang , Xuechen Liu , Xin Wang , Junichi Yamagishi , Yanmin Qian

There has long been plenty of theoretical and empirical evidence supporting the success of ensemble learning. Deep ensembles in particular take advantage of training randomness and expressivity of individual neural networks to gain…

Machine Learning · Computer Science 2024-03-21 Anh Bui , Vy Vo , Tung Pham , Dinh Phung , Trung Le

Analyzing geometric properties of high-dimensional loss functions, such as local curvature and the existence of other optima around a certain point in loss space, can help provide a better understanding of the interplay between neural…

Machine Learning · Computer Science 2024-02-22 Lucas Böttcher , Gregory Wheeler

We analyze the training dynamics for deep linear networks using a new metric - layer imbalance - which defines the flatness of a solution. We demonstrate that different regularization methods, such as weight decay or noise data…

Machine Learning · Computer Science 2020-07-21 Boris Ginsburg

Recent work has shown that methods like SAM which either explicitly or implicitly penalize second order information can improve generalization in deep learning. Seemingly similar methods like weight noise and gradient penalties often fail…

Machine Learning · Computer Science 2024-01-26 Yann N. Dauphin , Atish Agarwala , Hossein Mobahi

For linear classifiers, the relationship between (normalized) output margin and generalization is captured in a clear and simple bound -- a large output margin implies good generalization. Unfortunately, for deep models, this relationship…

Machine Learning · Computer Science 2021-06-17 Colin Wei , Tengyu Ma

The Hessian of neural networks can be decomposed into a sum of two matrices: (i) the positive semidefinite generalized Gauss-Newton matrix G, and (ii) the matrix H containing negative eigenvalues. We observe that for wider networks,…

Machine Learning · Computer Science 2020-01-15 Etai Littwin , Lior Wolf

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

Recent works have cast some light on the mystery of why deep nets fit any data and generalize despite being very overparametrized. This paper analyzes training and generalization for a simple 2-layer ReLU net with random initialization, and…

Machine Learning · Computer Science 2019-05-28 Sanjeev Arora , Simon S. Du , Wei Hu , Zhiyuan Li , Ruosong Wang

Recently, there has been growing evidence that if the width and depth of a neural network are scaled toward the so-called rich feature learning limit (\mup and its depth extension), then some hyperparameters -- such as the learning rate --…

Machine Learning · Computer Science 2024-11-14 Lorenzo Noci , Alexandru Meterez , Thomas Hofmann , Antonio Orvieto

It has been recently observed in much of the literature that neural networks exhibit a bottleneck rank property: for larger depths, the activation and weights of neural networks trained with gradient-based methods tend to be of…

Machine Learning · Computer Science 2025-11-26 Antoine Ledent , Rodrigo Alves , Yunwen Lei

We study the computational complexity of (deterministic or randomized) algorithms based on point samples for approximating or integrating functions that can be well approximated by neural networks. Such algorithms (most prominently…

Machine Learning · Computer Science 2021-04-08 Philipp Grohs , Felix Voigtlaender

The ability of overparameterized deep networks to interpolate noisy data, while at the same time showing good generalization performance, has been recently characterized in terms of the double descent curve for the test error. Common…

Machine Learning · Computer Science 2023-04-11 Matteo Gamba , Erik Englesson , Mårten Björkman , Hossein Azizpour

Generalization is the ability of a model to predict on unseen domains and is a fundamental task in machine learning. Several generalization bounds, both theoretical and empirical have been proposed but they do not provide tight bounds .In…

Machine Learning · Computer Science 2021-01-19 Sumukh Aithal K , Dhruva Kashyap , Natarajan Subramanyam

We initiate a program of average smoothness analysis for efficiently learning real-valued functions on metric spaces. Rather than using the Lipschitz constant as the regularizer, we define a local slope at each point and gauge the function…

Statistics Theory · Mathematics 2020-11-10 Yair Ashlagi , Lee-Ad Gottlieb , Aryeh Kontorovich

Most theoretical studies explaining the regularization effect in deep learning have only focused on gradient descent with a sufficient small learning rate or even gradient flow (infinitesimal learning rate). Such researches, however, have…

Machine Learning · Computer Science 2020-12-17 Wei Huang , Weitao Du , Richard Yi Da Xu , Chunrui Liu

Understanding when neural networks can be learned efficiently is a fundamental question in learning theory. Existing hardness results suggest that assumptions on both the input distribution and the network's weights are necessary for…

Machine Learning · Computer Science 2023-10-05 Amit Daniely , Nathan Srebro , Gal Vardi

Zeroth-order methods are extensively used in machine learning applications where gradients are infeasible or expensive to compute, such as black-box attacks, reinforcement learning, and language model fine-tuning. Existing optimization…

Machine Learning · Computer Science 2025-11-12 Liang Zhang , Bingcong Li , Kiran Koshy Thekumparampil , Sewoong Oh , Michael Muehlebach , Niao He

In recent years, continual learning, a prediction setting in which the problem environment may evolve over time, has become an increasingly popular research field due to the framework's gearing towards complex, non-stationary objectives.…

Machine Learning · Computer Science 2024-09-27 Max Koster , Jude Kukla