English
Related papers

Related papers: Data Distributional Properties As Inductive Bias f…

200 papers

Deep neural networks are renowned for their ability to generalise well across diverse tasks, even when heavily overparameterized. Existing works offer only partial explanations (for example, the NTK-based task-model alignment explanation…

Machine Learning · Computer Science 2025-06-02 Chris Mingard , Lukas Seier , Niclas Göring , Andrei-Vlad Badelita , Charles London , Ard Louis

Data selection plays a crucial role in data-driven decision-making, including in large language models (LLMs), and is typically task-dependent. Properties such as data quality and diversity have been extensively studied and are known to…

Machine Learning · Computer Science 2025-09-30 Yuqing Wang , Shangding Gu

Multiplicative stochasticity such as Dropout improves the robustness and generalizability of deep neural networks. Here, we further demonstrate that always-on multiplicative stochasticity combined with simple threshold neurons are…

Machine Learning · Computer Science 2019-10-29 Georgios Detorakis , Sourav Dutta , Abhishek Khanna , Matthew Jerry , Suman Datta , Emre Neftci

Understanding and controlling biasing effects in neural networks is crucial for ensuring accurate and fair model performance. In the context of classification problems, we provide a theoretical analysis demonstrating that the structure of a…

Machine Learning · Computer Science 2024-11-11 Emanuele Francazi , Aurelien Lucchi , Marco Baity-Jesi

What enables Stochastic Gradient Descent (SGD) to achieve better generalization than Gradient Descent (GD) in Neural Network training? This question has attracted much attention. In this paper, we study the distribution of the Stochastic…

Machine Learning · Computer Science 2019-10-28 Abhishek Panigrahi , Raghav Somani , Navin Goyal , Praneeth Netrapalli

Imitation learning holds the promise of equipping robots with versatile skills by learning from expert demonstrations. However, policies trained on finite datasets often struggle to generalize beyond the training distribution. In this work,…

Machine Learning · Computer Science 2025-04-28 Yixiao Wang

Deep neural networks are often trained in the over-parametrized regime (i.e. with far more parameters than training examples), and understanding why the training converges to solutions that generalize remains an open problem. Several…

Machine Learning · Statistics 2018-03-23 Hartmut Maennel , Olivier Bousquet , Sylvain Gelly

Stochastic Gradient Descent (SGD) has proven to be remarkably effective in optimizing deep neural networks that employ ever-larger numbers of parameters. Yet, improving the efficiency of large-scale optimization remains a vital and highly…

Machine Learning · Computer Science 2020-11-11 Frithjof Gressmann , Zach Eaton-Rosen , Carlo Luschi

Understanding the asymptotic behavior of gradient-descent training of deep neural networks is essential for revealing inductive biases and improving network performance. We derive the infinite-time training limit of a mathematically…

Machine Learning · Statistics 2022-02-08 Samuel Lippl , L. F. Abbott , SueYeon Chung

In this work, we theoretically investigate the generalization properties of neural networks (NN) trained by stochastic gradient descent (SGD) algorithm with large learning rates. Under such a training regime, our finding is that, the…

Machine Learning · Computer Science 2023-10-27 Miao Lu , Beining Wu , Xiaodong Yang , Difan Zou

Despite the remarkable performance of generative Diffusion Models (DMs), their internal working is still not well understood, which is potentially problematic. This paper focuses on exploring the important notion of bias-variance tradeoff…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Shahin Hakemi , Naveed Akhtar , Ghulam Mubashar Hassan , Ajmal Mian

Despite impressive performance as evaluated on i.i.d. holdout data, deep neural networks depend heavily on superficial statistics of the training data and are liable to break under distribution shift. For example, subtle changes to the…

Computer Vision and Pattern Recognition · Computer Science 2019-03-18 Haohan Wang , Zexue He , Zachary C. Lipton , Eric P. Xing

We introduce a novel training principle for probabilistic models that is an alternative to maximum likelihood. The proposed Generative Stochastic Networks (GSN) framework is based on learning the transition operator of a Markov chain whose…

Machine Learning · Computer Science 2015-03-29 Guillaume Alain , Yoshua Bengio , Li Yao , Jason Yosinski , Eric Thibodeau-Laufer , Saizheng Zhang , Pascal Vincent

We investigate the dynamical and convergent properties of stochastic gradient descent (SGD) applied to Deep Neural Networks (DNNs). Characterizing the relation between learning rate, batch size and the properties of the final minima, such…

Machine Learning · Computer Science 2018-09-14 Stanisław Jastrzębski , Zachary Kenton , Devansh Arpit , Nicolas Ballas , Asja Fischer , Yoshua Bengio , Amos Storkey

We analyze the masked language modeling pretraining objective function from the perspective of the distributional hypothesis. We investigate whether better sample efficiency and the better generalization capability of models pretrained with…

Computation and Language · Computer Science 2023-10-26 Ting-Rui Chiang , Dani Yogatama

Modern approaches to supervised learning like deep neural networks (DNNs) typically implicitly assume that observed responses are statistically independent. In contrast, correlated data are prevalent in real-life large-scale applications,…

Machine Learning · Statistics 2023-01-30 Giora Simchoni , Saharon Rosset

Understanding the inductive bias and generalization properties of large overparametrized machine learning models requires to characterize the dynamics of the training algorithm. We study the learning dynamics of large two-layer neural…

Machine Learning · Statistics 2025-10-30 Andrea Montanari , Pierfrancesco Urbani

Deep neural networks (DNNs) achieve remarkable performance on a wide range of tasks, yet their mathematical analysis remains fragmented: stability and generalization are typically studied in disparate frameworks and on a case-by-case basis.…

Machine Learning · Statistics 2026-01-29 Jonathan Vacher

Batch Normalization (BN) has been a standard component in designing deep neural networks (DNNs). Although the standard BN can significantly accelerate the training of DNNs and improve the generalization performance, it has several…

Machine Learning · Computer Science 2020-10-13 Yong Guo , Qingyao Wu , Chaorui Deng , Jian Chen , Mingkui Tan

The generalization mystery in deep learning is the following: Why do over-parameterized neural networks trained with gradient descent (GD) generalize well on real datasets even though they are capable of fitting random datasets of…

Machine Learning · Computer Science 2022-06-07 Satrajit Chatterjee , Piotr Zielinski
‹ Prev 1 3 4 5 6 7 10 Next ›