English
Related papers

Related papers: Avoiding The Double Descent Phenomenon of Random F…

200 papers

In response to the prevalent challenge of overfitting in deep neural networks, this paper introduces Simultaneous Learning, a regularization approach drawing on principles of Transfer Learning and Multi-task Learning. We leverage auxiliary…

We study generalised linear regression and classification for a synthetically generated dataset encompassing different problems of interest, such as learning with random features, neural networks in the lazy training regime, and the hidden…

Statistics Theory · Mathematics 2022-03-28 Federica Gerace , Bruno Loureiro , Florent Krzakala , Marc Mézard , Lenka Zdeborová

Data scarcity drives the need for more sample-efficient large language models. In this work, we use the double descent phenomenon to holistically compare the sample efficiency of discrete diffusion and autoregressive models. We show that…

Machine Learning · Computer Science 2025-09-30 Ahmad Fraij , Sam Dauncey

Regularization approaches have demonstrated their effectiveness for solving ill-posed problems. However, in the context of variational restoration methods, a challenging question remains, which is how to find a good regularizer. While total…

Optimization and Control · Mathematics 2011-10-25 Nelly Pustelnik , Caroline Chaux , Jean-Christophe Pesquet

Model collapse occurs when generative models degrade after repeatedly training on their own synthetic outputs. We study this effect in overparameterized linear regression in a setting where each iteration mixes fresh real labels with…

Machine Learning · Statistics 2026-02-13 Anvit Garg , Sohom Bhattacharya , Pragya Sur

Catastrophic overfitting is a phenomenon observed during Adversarial Training (AT) with the Fast Gradient Sign Method (FGSM) where the test robustness steeply declines over just one epoch in the training stage. Prior work has attributed…

Machine Learning · Computer Science 2021-11-23 Varun Sivashankar , Nikil Selvam

The double descent (DD) paradox, where over-parameterized models see generalization improve past the interpolation point, remains largely unexplored in the non-stationary domain of Deep Reinforcement Learning (DRL). We present preliminary…

Machine Learning · Computer Science 2025-11-11 Viktor Veselý , Aleksandar Todorov , Matthia Sabatelli

The weight decay regularization term is widely used during training to constrain expressivity, avoid overfitting, and improve generalization. Historically, this concept was borrowed from the SVM maximum margin principle and extended to…

Machine Learning · Computer Science 2021-10-12 Berry Weinstein , Shai Fine , Yacov Hel-Or

Normalization methods such as batch [Ioffe and Szegedy, 2015], weight [Salimansand Kingma, 2016], instance [Ulyanov et al., 2016], and layer normalization [Baet al., 2016] have been widely used in modern machine learning. Here, we study the…

Machine Learning · Computer Science 2022-08-31 Xiaoxia Wu , Edgar Dobriban , Tongzheng Ren , Shanshan Wu , Zhiyuan Li , Suriya Gunasekar , Rachel Ward , Qiang Liu

Multimodal learning, particularly for pedestrian detection, has recently received emphasis due to its capability to function equally well in several critical autonomous driving scenarios such as low-light, night-time, and adverse weather…

Computer Vision and Pattern Recognition · Computer Science 2023-07-10 Arindam Das , Sudip Das , Ganesh Sistu , Jonathan Horgan , Ujjwal Bhattacharya , Edward Jones , Martin Glavin , Ciarán Eising

Overfitting frequently occurs in deep learning. In this paper, we propose a novel regularization method called Drop-Activation to reduce overfitting and improve generalization. The key idea is to drop nonlinear activation functions by…

Machine Learning · Computer Science 2020-03-31 Senwei Liang , Yuehaw Khoo , Haizhao Yang

Visual retrieval system faces frequent model update and deployment. It is a heavy workload to re-extract features of the whole database every time.Feature compatibility enables the learned new visual features to be directly compared with…

Computer Vision and Pattern Recognition · Computer Science 2021-08-09 Yan Bai , Jile Jiao , Shengsen Wu , Yihang Lou , Jun Liu , Xuetao Feng , Ling-Yu Duan

We study the problem of learning an unknown function using random feature models. Our main contribution is an exact asymptotic analysis of such learning problems with Gaussian data. Under mild regularity conditions for the feature matrix,…

Information Theory · Computer Science 2020-08-28 Oussama Dhifallah , Yue M. Lu

This paper aims to compare different regularization strategies to address a common phenomenon, severe overfitting, in embedding-based neural networks for NLP. We chose two widely studied neural models and tasks as our testbed. We tried…

Computation and Language · Computer Science 2015-08-18 Hao Peng , Lili Mou , Ge Li , Yunchuan Chen , Yangyang Lu , Zhi Jin

Recent successes of massively overparameterized models have inspired a new line of work investigating the underlying conditions that enable overparameterized models to generalize well. This paper considers a framework where the possibly…

Machine Learning · Computer Science 2023-12-06 Martin Hellkvist , Ayça Özçelikkale , Anders Ahlén

Data augmentation methods are commonly integrated into the training of anomaly detection models. Previous approaches have primarily focused on replicating real-world anomalies or enhancing diversity, without considering that the standard of…

Artificial Intelligence · Computer Science 2024-12-30 Jiang Lin , Yaping Yan

Despite being highly over-parametrized, and having the ability to fully interpolate the training data, deep networks are known to generalize well to unseen data. It is now understood that part of the reason for this is that the training…

Machine Learning · Computer Science 2023-02-21 Danil Akhtiamov , Babak Hassibi

There is growing body of learning problems for which it is natural to organize the parameters into matrix, so as to appropriately regularize the parameters under some matrix norm (in order to impose some more sophisticated prior knowledge).…

Machine Learning · Computer Science 2010-10-19 Sham M. Kakade , Shai Shalev-Shwartz , Ambuj Tewari

The recent advances in deep clustering have been made possible by significant progress in self-supervised and pseudo-supervised learning. However, the trade-off between self-supervision and pseudo-supervision can give rise to three primary…

Computer Vision and Pattern Recognition · Computer Science 2025-03-06 Amal Shaheena , Nairouz Mrabahb , Riadh Ksantinia , Abdulla Alqaddoumia

We perform an average case analysis of the generalization dynamics of large neural networks trained using gradient descent. We study the practically-relevant "high-dimensional" regime where the number of free parameters in the network is on…

Machine Learning · Statistics 2017-10-11 Madhu S. Advani , Andrew M. Saxe
‹ Prev 1 3 4 5 6 7 10 Next ›