English
Related papers

Related papers: Optimal Regularization Can Mitigate Double Descent

200 papers

Regularizing neural networks is important for anticipating model behavior in regions of the data space that are not well represented. In this work, we propose a regularization technique for enforcing a level of smoothness in the mapping…

Machine Learning · Computer Science 2025-03-05 Ali Hasan , Haoming Yang , Yuting Ng , Vahid Tarokh

We investigate changing the bandwidth of a translational-invariant kernel during training when solving kernel regression with gradient descent. We present a theoretical bound on the out-of-sample generalization error that advocates for…

Machine Learning · Statistics 2025-05-19 Oskar Allerbo

We propose self-adaptive training -- a unified training algorithm that dynamically calibrates and enhances training processes by model predictions without incurring an extra computational cost -- to advance both supervised and…

Machine Learning · Computer Science 2022-10-17 Lang Huang , Chao Zhang , Hongyang Zhang

We consider networks, trained via stochastic gradient descent to minimize $\ell_2$ loss, with the training labels perturbed by independent noise at each iteration. We characterize the behavior of the training dynamics near any parameter…

Machine Learning · Computer Science 2020-07-23 Guy Blanc , Neha Gupta , Gregory Valiant , Paul Valiant

Regularization, whether explicit in terms of a penalty in the loss or implicit in the choice of algorithm, is a cornerstone of modern machine learning. Indeed, controlling the complexity of the model class is particularly important when…

Machine Learning · Statistics 2024-10-22 Matteo Vilucchio , Nikolaos Tsilivis , Bruno Loureiro , Julia Kempe

Data subset selection from a large number of training instances has been a successful approach toward efficient and cost-effective machine learning. However, models trained on a smaller subset may show poor generalization ability. In this…

Machine Learning · Computer Science 2021-06-24 Durga Sivasubramanian , Rishabh Iyer , Ganesh Ramakrishnan , Abir De

We conjecture that the inherent difference in generalisation between adaptive and non-adaptive gradient methods in deep learning stems from the increased estimation noise in the flattest directions of the true loss surface. We demonstrate…

Machine Learning · Statistics 2022-03-17 Diego Granziol , Nicholas Baskerville

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

Emergent behaviors are in the focus of recent research interest. It is then of considerable importance to investigate what optimizations suit the learning and prediction of chaotic systems, the putative candidates for emergence. We have…

Machine Learning · Computer Science 2007-05-23 Z. Szabo , A. Lorincz

One of the mysteries in the success of neural networks is randomly initialized first order methods like gradient descent can achieve zero training loss even though the objective function is non-convex and non-smooth. This paper demystifies…

Machine Learning · Computer Science 2019-02-06 Simon S. Du , Xiyu Zhai , Barnabas Poczos , Aarti Singh

Recent theoretical studies illustrated that kernel ridgeless regression can guarantee good generalization ability without an explicit regularization. In this paper, we investigate the statistical properties of ridgeless regression with…

Machine Learning · Computer Science 2023-08-30 Jian Li , Yong Liu , Yingying Zhang

Randomized dimensionality reduction is a widely-used algorithmic technique for speeding up large-scale Euclidean optimization problems. In this paper, we study dimension reduction for a variety of maximization problems, including…

Data Structures and Algorithms · Computer Science 2025-06-03 Jie Gao , Rajesh Jayaram , Benedikt Kolbe , Shay Sapir , Chris Schwiegelshohn , Sandeep Silwal , Erik Waingarten

Machine unlearning algorithms aim to remove the impact of selected training data from a model without the computational expenses of retraining from scratch. Two such algorithms are ``Descent-to-Delete" (D2D) and ``Rewind-to-Delete" (R2D),…

Machine Learning · Computer Science 2026-03-02 Siqiao Mu , Diego Klabjan

In deep learning, often the training process finds an interpolator (a solution with 0 training loss), but the test loss is still low. This phenomenon, known as benign overfitting, is a major mystery that received a lot of recent attention.…

Machine Learning · Computer Science 2023-05-29 Mo Zhou , Rong Ge

In overparameterized logistic regression, gradient descent (GD) iterates diverge in norm while converging in direction to the maximum $\ell_2$-margin solution -- a phenomenon known as the implicit bias of GD. This work investigates…

Machine Learning · Computer Science 2025-07-01 Jingfeng Wu , Peter Bartlett , Matus Telgarsky , Bin Yu

We investigate the asymptotic risk of a general class of overparameterized likelihood models, including deep models. The recent empirical success of large-scale models has motivated several theoretical studies to investigate a scenario…

Machine Learning · Statistics 2021-03-16 Ryumei Nakada , Masaaki Imaizumi

In this paper, we propose a coupled tensor norm regularization that could enable the model output feature and the data input to lie in a low-dimensional manifold, which helps us to reduce overfitting. We show this regularization term is…

Optimization and Control · Mathematics 2023-02-24 Ying Gao , Yunfei Qu , Chunfeng Cui , Deren Han

Designing learning algorithms that are resistant to perturbations of the underlying data distribution is a problem of wide practical and theoretical importance. We present a general approach to this problem focusing on unsupervised…

Machine Learning · Computer Science 2021-02-22 Andreas Maurer , Daniela A. Parletta , Andrea Paudice , Massimiliano Pontil

We develop regularization methods to find flat minima while training deep neural networks. These minima generalize better than sharp minima, yielding models outperforming baselines on real-world test data (which may be distributed…

Machine Learning · Computer Science 2025-07-04 Adam Sandler , Diego Klabjan , Yuan Luo

Extreme learning machine (ELM) is a network model that arbitrarily initializes the first hidden layer and can be computed speedily. In order to improve the classification performance of ELM, a $\ell_2$ and $\ell_{0.5}$ regularization ELM…

Optimization and Control · Mathematics 2023-01-05 Liangjuan Zhou , Wei Miao