1 citations · 2 across the 34 of their papers we have counts for
10 papers · 1 filter
The Effect of Layer Ordering in Hybrid Architectures
John Cooper, Mingchen Ma, Jiaqi Mo +4
Hybrid attention is rapidly becoming the dominant architectural choice for frontier models. Despite their successes, such architectures complicate model design by introducing addit…
Adaptive Robust Confidence Sets in High Dimensions
Ilias Diakonikolas, Chao Gao, Daniel M. Kane +1
We study adaptive confidence sets for mean vectors of multivariate Gaussians with identity covariance under Huber contamination when the contamination proportion is unknown. We sho…
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…
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…
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…
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…
Expressivity-Efficiency Tradeoffs for Hybrid Sequence Models
John Cooper, Ilias Diakonikolas, Mingchen Ma +1
Hybrid sequence models--combining Transformer and state-space model layers--seek to gain the expressive versatility of attention as well as the computational efficiency of state-sp…
High-Dimensional Gaussian Mean Estimation under Realizable Contamination
Ilias Diakonikolas, Daniel M. Kane, Thanasis Pittas
We study mean estimation for a Gaussian distribution with identity covariance in under a missing data scheme termed realizable -contamination model. In this model…
Testable Learning of General Halfspaces under Massart Noise
Ilias Diakonikolas, Giannis Iakovidis, Daniel M. Kane +1
We study the algorithmic task of testably learning general Massart halfspaces under the Gaussian distribution. In the testable learning setting, the aim is the design of a tester-l…
Sample Complexity Bounds for Robust Mean Estimation with Mean-Shift Contamination
Ilias Diakonikolas, Giannis Iakovidis, Daniel M. Kane +1
We study the basic task of mean estimation in the presence of mean-shift contamination. In the mean-shift contamination model, an adversary is allowed to replace a small constant f…