English
Related papers

Related papers: Double Descent Risk and Volume Saturation Effects:…

200 papers

We develop a systemic risk framework to explore cascading systemic failures in networked control systems. A time-delayed version of the vehicle platooning problem is used as a benchmark to study the interplay among network connectivity,…

Systems and Control · Electrical Eng. & Systems 2022-02-15 Guangyi Liu , Christoforos Somarakis , Nader Motee

In this paper, we provide new theoretical results on the generalization properties of learning algorithms for multiclass classification problems. The originality of our work is that we propose to use the confusion matrix of a classifier as…

Machine Learning · Computer Science 2012-05-25 Pierre Machart , Liva Ralaivola

Learning algorithms that divide the data into batches are prevalent in many machine-learning applications, typically offering useful trade-offs between computational efficiency and performance. In this paper, we examine the benefits of…

Machine Learning · Computer Science 2024-09-24 Shahar Stein Ioushua , Inbar Hasidim , Ofer Shayevitz , Meir Feder

The development and use of dimension reduction methods is prevalent in modern statistical literature. This paper reviews a class of dimension reduction techniques which aim to simultaneously select relevant predictors and find clusters…

Methodology · Statistics 2022-02-18 Suchit Mehrotra

Data augmentation is one of the most widely used techniques to improve generalization in modern machine learning, often justified by its ability to promote invariance to label-irrelevant transformations. However, its theoretical role…

Machine Learning · Computer Science 2026-02-17 Abdelali Bouyahia , Frédéric LeBlanc , Mario Marchand

Random feature ridge regression is often analyzed in the high-dimensional regime under the homogeneous sampling model $x_i=\Sigma^{1/2}x_i'$, where the vectors $x_i'$ have iid entries and the same covariance matrix $\Sigma$ is shared by all…

Machine Learning · Statistics 2026-05-19 Issa-Mbenard Dabo , Jérémie Bigot

This paper studies an intriguing phenomenon related to the good generalization performance of estimators obtained by using large learning rates within gradient descent algorithms. First observed in the deep learning literature, we show that…

Machine Learning · Statistics 2022-06-06 Gaspard Beugnot , Julien Mairal , Alessandro Rudi

The last layer of neural language models (LMs) projects output features of dimension $D$ to logits in dimension $V$, the size of the vocabulary, where usually $D \ll V$. This mismatch is known to raise risks of limited expressivity in…

Computation and Language · Computer Science 2026-03-12 Nathan Godey , Yoav Artzi

Working in the limit in which the localization length scale is large compared to other relevant length scales we examine three experimental situations with the continuous spontaneous localization (CSL) model---a well-motivated alternative…

Quantum Physics · Physics 2014-04-02 Daniel Bedingham

This paper deals with order identification for nested models in the i.i.d. framework. We study the asymptotic efficiency of two generalized likelihood ratio tests of the order. They are based on two estimators which are proved to be…

Statistics Theory · Mathematics 2007-06-13 Antoine Chambaz

We present a two-dimensional mesoscopic model of a yield stress material that includes the possibility of local volume fluctuations coupled to shear, in such a way that the shear strength of the material decreases as the local density…

Materials Science · Physics 2022-08-31 E. A. Jagla

Variable selection in linear regression has been a central topic in statistical research for decades. Bayesian variable selection methods, which account for uncertainty in both the regression coefficients and the noise variance, have…

Methodology · Statistics 2026-04-24 Leo L Duan

Metric embedding has become a common technique in the design of algorithms. Its applicability is often dependent on how high the embedding's distortion is. For example, embedding finite metric space into trees may require linear distortion…

Data Structures and Algorithms · Computer Science 2007-05-23 Yair Bartal , Manor Mendel

This work studies embedding of arbitrary VC classes in well-behaved VC classes, focusing particularly on extremal classes. Our main result expresses an impossibility: such embeddings necessarily require a significant increase in dimension.…

Discrete Mathematics · Computer Science 2024-05-28 Zachary Chase , Bogdan Chornomaz , Steve Hanneke , Shay Moran , Amir Yehudayoff

We study double descent and benign overfitting in macroeconomic forecasting. We document that double-descent risk curves arise in standard macroeconomic datasets that are driven by a small number of latent factors, and we characterize when…

Econometrics · Economics 2026-05-18 Andrea Carriero , Florian Huber , Davide Pettenuzzo

We address the problem of the achievable regret rates with online logistic regression. We derive lower bounds with logarithmic regret under $L_1$, $L_2$, and $L_\infty$ constraints on the parameter values. The bounds are dominated by $d/2…

Machine Learning · Computer Science 2020-02-20 Gil I. Shamir

Neural networks have been successfully used for classification tasks in a rapidly growing number of practical applications. Despite their popularity and widespread use, there are still many aspects of training and classification that are…

Machine Learning · Computer Science 2016-05-03 Ewout van den Berg

We derive high-dimensional Gaussian comparison results for the standard $V$-fold cross-validated risk estimates. Our results combine a recent stability-based argument for the low-dimensional central limit theorem of cross-validation with…

Statistics Theory · Mathematics 2023-11-15 Nicholas Kissel , Jing Lei

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

Learning dynamics from dissipative chaotic systems is notoriously difficult due to their inherent instability, as formalized by their positive Lyapunov exponents, which exponentially amplify errors in the learned dynamics. However, many of…

Machine Learning · Computer Science 2024-06-07 Yair Schiff , Zhong Yi Wan , Jeffrey B. Parker , Stephan Hoyer , Volodymyr Kuleshov , Fei Sha , Leonardo Zepeda-Núñez