Robust Statistics

Latest papers

17 papers3 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Efficient and Optimal Learning of Discrete Distributions with Person-Level Privacy
Oct 22, 2026Gautam Kamath, Mahbod Majid, Ankur Moitra +2Robust Statistics Differential Privacy
New York University · Massachusetts Institute of Technology · University of Texas at Austin and University of Waterloo +1
From Proper Scoring Rules and Edge Biases to Mumford-Shah Models: Robust Unsupervised Hyperspectral Image Segmentation
Oct 20, 2026Fabian Conrad, Benjamin BerkelsRobust Statistics Remote Sensing Image Segmentation
IGPM, RWTH Aachen University, Germany
Adaptive Robust Confidence Sets in High Dimensions
Oct 11, 2026Ilias Diakonikolas, Chao Gao, Daniel M. Kane +1Robust Mean Estimation Low-Degree Polynomial Method
University of Wisconsin-Madison · University of Chicago · University of California, San Diego +1
Sparse Regression Distilled from a Single Robust Fit
Sep 20, 2026Wooyoung Shin, Seunghwan ParkRobust Regression Linear Regression
Department of Information Statistics, Kangwon National University, 1, Kangwondaehak-gil, Chuncheon-si, Gangwon-do, 24341, Republic of Korea.
Median-of-Means as an Extremal Convex Estimator and a Nonconvex Route to the Trimmed Oracle
Sep 1, 2026Angshul MajumdarNonconvex Optimization Robust Mean Estimation
Department of Electronics and Communications Engineering, IIIT Delhi, India
No Unique Minimizer, No Problem: On the Consistency of Robust Neural Classifiers
Aug 9, 2026Subhabrata Majumdar, Anand Deo, Partha Pratim Saha +1Robust Estimation Neural Network Robustness
Indian Institute of Management Bangalore · Independent Researcher · Indian Statistical Institute, Kolkata
HOMER: Huber-of-Means for Efficient and Robust Estimation in Hilbert Spaces
Jul 29, 2026Kisung You, Boram ChoRobust Mean Estimation Heavy-Tailed Distributions
Baruch College · Yale University
Robust Diffusion Models via Divergence-Induced Weighted Denoising
Jun 21, 2026Lei Li, Yuexiao DongNeural Network Robustness Robust Loss Functions
LunarAI LLC · Newark, DE 19702 · Fox School of Business +1
Robust Moment-Based Estimation via Spectral Gradient Reweighting
May 26, 2026Liu Zhang, Amit SingerRobust Statistics Robust Estimation
Program in Applied and Computational Mathematics, Princeton University, Princeton, NJ 08544 USA · Department of Mathematics and Program in Applied and Computational Mathematics, Princeton University, Princeton, NJ 08544 USA
Byzantine-Robust Distributed Sparse Learning Revisited
May 13, 2026Yuxuan Wang, Lixin Zhang, Kangqiang LiDistributed Training Distributed Optimization
School of Mathematical Sciences, Zhejiang University, Hangzhou, 310027, Zhejiang, China · School of Statistics and Mathematics, Zhejiang Gongshang University, Hangzhou, 310018, Zhejiang, China · Information Center, Hubei Provincial Tobacco Monopoly Administration, Wuhan, 430030, Hubei, China
Conformal Robust Set Estimation
Apr 20, 2026Alejandro Cholaquidis, Emilien Joly, Leonardo MorenoConformal Prediction Robust Estimation
*Centro de Matem´atica, Facultad de Ciencias, Universidad de la Rep´ublica, Uruguay · †Centro de Investigaci´on en Matem´aticas (CIMAT), M´exico · ‡Departamento de M´etodos Cuantitativos, Facultad de Ciencias Econ´omicas y de Administraci´on, Universidad de la Rep´ublica, Uruguay
Horospherical Depth and Busemann Median on Hadamard Manifolds
Apr 20, 2026Yangdi Jiang, Xiaotian Chang, Cyrus MostajeranRobust Statistics
Division of Mathematical Sciences, Nanyang Technological University
Computation of Least Trimmed Squares: A Branch-and-Bound framework with Hyperplane Arrangement Enhancements
Apr 13, 2026Xiang Meng, Andrés Gómez, Rahul MazumderRobust Regression Robust Statistics
MIT Operations Research Center · USC Daniel J. Epstein Department of Industrial and Systems Engineering · MIT Sloan School of Management, Operations Research Center
EB-RANSAC: Random Sample Consensus based on Energy-Based Model
Mar 12, 2026Muneki Yasuda, Nao Watanabe, Kaiji SekimotoRobust Estimation Robust Statistics
Graduate School of Science and Engineering, Yamagata University · TSCSK Corporation
ForwardFlow: Simulation only statistical inference using deep learning
Mar 11, 2026Stefan BöhringerRobust Statistics Simulation-Based Inference
Department of Biomedical Data Sciences Leiden University Medical Center Einthovenweg 20, 2333 ZC Leiden, The Netherlands
Medix: Out-of-Distribution Detection from Unlabeled Wild Data via Robust Gradient Statistics
Oct 7, 2025Momin Abbas, Ali Falahati, Hossein Goli +1OOD Detection Robust Statistics
IBM · University of Waterloo · CUHK +1
Robust Linear Predictions: Analyses of Uniform Concentration, Fast Rates and Model Misspecification
Jan 6, 2022Saptarshi Chakraborty, Debolina Paul, Swagatam DasRobust Regression Model Misspecification
Department of Statistics, University of California, Berkeley · Department of Statistics, Stanford University · Electronics and Communication Sciences Unit, Indian Statistical Institute, Kolkata, India

Oct 22, 2026J/K move · Enter open · S save

Efficient and Optimal Learning of Discrete Distributions with Person-Level Privacy

Gautam Kamath, Mahbod Majid, Ankur Moitra, Argyris Mouzakis+1

New York University · Massachusetts Institute of Technology · University of Texas at Austin and University of Waterloo+1

Robust Statistics Differential Privacy Statistical Learning Theory

Open paper AskPDF arXiv

We study learning a discrete distribution under person-level differential privacy in the batched setting. Given

n

users, each contributing

m

i.i.d. samples from an unknown distribution

μ

over

[k]

, we seek an estimate of

μ

with total-variation error

α

. We give polynomial-time algorithms under both pure and approximate differential privacy. Under pure

(\varepsilon,0)

-DP, we achieve

n = \widetilde O(k/(α^2 m)+k/(α\sqrt{m}\varepsilon)+k/\varepsilon)

, the first polynomial-time pure-DP guarantee matching the information-theoretic optimum up to logarithmic factors. Under approximate

(\varepsilon,δ)

-DP, we achieve

n = \widetilde O(k/(α^2 m)+k/(α\sqrt{m}\varepsilon)+k+\log(1/δ)/\varepsilon)

. At

δ=2^{-Θ(k)}

, this is

\widetilde O(k)

for fixed

α,\varepsilon,m

and failure probability. Our algorithms use a new degree-6 sum-of-squares estimator for learning from untrusted batches. Its key ingredient is a trace-bounded diagonal majorizer for the difference between the empirical covariance of the repaired batch averages and the multinomial covariance predicted by their mean. We prove that clean data admit this certificate through semidefinite-programming duality and a new application of the stronger symmetric form of Grothendieck's inequality due to Friedland and Lim. The certificate preserves the mean-dependent variance of multinomial batch averages, yielding the near-optimal robust rate

O(η\sqrt{\log(1/η)/m})

and providing the score required by the privacy reduction. We also prove a statistical query lower bound ruling out a uniformly smaller order of error under fixed polynomial SQ resource bounds.