works on

From the 2 of 25 linked papers with an AI index.

activity
20242026
collaborators

25 papers

cs.LG2026

High-Dimensional Gaussian Mean Estimation under Realizable Contamination

Ilias Diakonikolas, Daniel M. Kane, Thanasis Pittas

The paper investigates estimating the mean of a high‑dimensional Gaussian when each sample may be missing with a bounded, data‑dependent probability (realizable ε‑contamination), p…

cs.DS2026

Linear Regression under Missing or Corrupted Coordinates

Ilias Diakonikolas, Jelena Diakonikolas, Daniel M. Kane +2

The paper analyzes multivariate linear regression with Gaussian features when an adversary can delete or corrupt a fraction of entries per coordinate, providing tight error bounds…

cs.LG2026

Efficiently Learning Drifting Halfspaces with Massart Noise

Mingchen Ma, Guyang Cao, Jelena Diakonikolas +1

We study the problem of learning a drifting concept in the presence of Massart noise. In this framework, an online learner has access to a history of independent samples whose labe…

cs.LG2026

Robust Regression of General ReLUs with Queries

Ilias Diakonikolas, Daniel M. Kane, Mingchen Ma

We study the task of agnostically learning general (as opposed to homogeneous) ReLUs under the Gaussian distribution with respect to the squared loss. In the passive learning setti…

cs.LG2026

Polynomial-Time Robust Multiclass Linear Classification under Gaussian Marginals

Ilias Diakonikolas, Giannis Iakovidis, Mingchen Ma

We study the task of agnostic learning of multiclass linear classifiers under the Gaussian distribution. Given labeled examples from a distribution over $\mathbb{R}^d \tim…

math.ST2026

Robust Regression with Adaptive Contamination in Response: Optimal Rates and Computational Barriers

Ilias Diakonikolas, Chao Gao, Daniel M. Kane +2

We study robust regression under a contamination model in which covariates are clean while the responses may be corrupted in an adaptive manner. Unlike the classical Huber's contam…