paper-with-me

홈 › Papers

Regularized Loss Minimizers with Local Data Perturbation: Consistency and Data Irrecoverability

2018-05-19 · Zitao Li, Jean Honorio

We introduce a new concept, data irrecoverability, and show that the well-studied concept of data privacy is sufficient but not necessary for data irrecoverability. We show that there are several regularized loss minimization problems that can use perturbed data with theoretical guarantees of generalization, i.e., loss consistency. Our results quantitatively connect the convergence rates of the learning problems to the impossibility for any adversary for recovering the original data from perturbed observations. In addition, we show several examples where the convergence rates with perturbed data only increase the convergence rates with original data within a constant factor related to the amount of perturbation, i.e., noise.

📄 PDF Abstract BibTeX arXiv:1805.07645

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

ERM and RERM are optimal estimators for regression problems when malicious outliers corrupt the labels

2019-10-24 · Geoffrey Chinot

We study Empirical Risk Minimizers (ERM) and Regularized Empirical Risk Minimizers (RERM) for regression problems with convex and $L$-Lipschitz loss functions. We consider a setting where $|\cO|$ malicious outliers conta…

regression

On the Loss Landscape Geometry of Regularized Deep Matrix Factorization: Uniqueness and Sharpness

2026-03-28 · Anil Kamber, Rahul Parhi arxiv

Weight decay is ubiquitous in training deep neural network architectures. Its empirical success is often attributed to capacity control; nonetheless, our theoretical understanding of its effect on the loss landscape and …

Piecewise Strong Convexity of Neural Networks

2018-10-30 · NeurIPS 2019 12 · Tristan Milne

We study the loss surface of a feed-forward neural network with ReLU non-linearities, regularized with weight decay. We show that the regularized loss function is piecewise strongly convex on an important open set which …

image-classificationImage ClassificationLearning Theory

A Mosco sufficient condition for intrinsic stability of non-unique convex Empirical Risk Minimization

2026-01-25 · Karim Bounja, Lahcen Laayouni, Abdeljalil Sakat arxiv

Empirical risk minimization (ERM) stability is usually studied via single-valued outputs, while convex non-strict losses yield set-valued minimizers. We identify Painlevé-Kuratowski upper semicontinuity (PK-u.s.c.) as th…

Label Noise SGD Provably Prefers Flat Global Minimizers

2021-06-11 · NeurIPS 2021 12 · Alex Damian, Tengyu Ma, Jason D. Lee

In overparametrized models, the noise in stochastic gradient descent (SGD) implicitly regularizes the optimization trajectory and determines which local minimum SGD converges to. Motivated by empirical studies that demon…