1 citations · 2 across the 30 of their papers we have counts for
33 papers
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…
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…
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…
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…
Statistical Query Lower Bounds for Smoothed Agnostic Learning
Ilias Diakonikolas, Daniel M. Kane
We study the complexity of smoothed agnostic learning, recently introduced by~\cite{CKKMS24}, in which the learner competes with the best classifier in a target class under slight…
PTF Testing Lower Bounds for Non-Gaussian Component Analysis
Ilias Diakonikolas, Daniel M. Kane, Sihan Liu +1
This work studies information-computation gaps for statistical problems. A common approach for providing evidence of such gaps is to show sample complexity lower bounds (that are s…
Information-Computation Tradeoffs for Noiseless Linear Regression with Oblivious Contamination
Ilias Diakonikolas, Chao Gao, Daniel M. Kane +2
We study the task of noiseless linear regression under Gaussian covariates in the presence of additive oblivious contamination. Specifically, we are given i.i.d.\ samples from a di…
Agnostic Product Mixed State Tomography via Robust Statistics
Alvan Arulandu, Ilias Diakonikolas, Daniel Kane +1
We study the complexity of two closely related learning problems, one quantum and one classical. In the quantum setting, we consider agnostic tomography for the natural class of pr…
Linear Regression under Missing or Corrupted Coordinates
Ilias Diakonikolas, Jelena Diakonikolas, Daniel M. Kane +2
We study multivariate linear regression under Gaussian covariates in two settings, where data may be erased or corrupted by an adversary under a coordinate-wise budget. In the inco…
Replicable Distribution Testing
Ilias Diakonikolas, Jingyi Gao, Daniel Kane +2
We initiate a systematic investigation of distribution testing in the framework of algorithmic replicability. Specifically, given independent samples from a collection of probabili…
On Fine-Grained Distinct Element Estimation
Ilias Diakonikolas, Daniel M. Kane, Jasper C. H. Lee +3
We study the problem of distributed distinct element estimation, where servers each receive a subset of a universe and aim to compute a -approximation to…
Algorithms and SQ Lower Bounds for Robustly Learning Real-valued Multi-index Models
Ilias Diakonikolas, Giannis Iakovidis, Daniel M. Kane +1
We study the complexity of learning real-valued Multi-Index Models (MIMs) under the Gaussian distribution. A -MIM is a function that depends only…
On Learning Parallel Pancakes with Mostly Uniform Weights
Ilias Diakonikolas, Daniel M. Kane, Sushrut Karmalkar +2
We study the complexity of learning -mixtures of Gaussians (-GMMs) on . This task is known to have complexity in full generality. To circumvent this…
Faster Algorithms for Agnostically Learning Disjunctions and their Implications
Ilias Diakonikolas, Daniel M. Kane, Lisheng Ren
We study the algorithmic task of learning Boolean disjunctions in the distribution-free agnostic PAC model. The best known agnostic learner for the class of disjunctions over $\{0,…
Batch List-Decodable Linear Regression via Higher Moments
Ilias Diakonikolas, Daniel M. Kane, Sushrut Karmalkar +2
We study the task of list-decodable linear regression using batches. A batch is called clean if it consists of i.i.d. samples from an unknown linear regression distribution. For a…
Efficient Multivariate Robust Mean Estimation Under Mean-Shift Contamination
Ilias Diakonikolas, Giannis Iakovidis, Daniel M. Kane +1
We study the algorithmic problem of robust mean estimation of an identity covariance Gaussian in the presence of mean-shift contamination. In this contamination model, we are given…
Robust Learning of Multi-index Models via Iterative Subspace Approximation
Ilias Diakonikolas, Giannis Iakovidis, Daniel M. Kane +1
We study the task of learning Multi-Index Models (MIMs) with label noise under the Gaussian distribution. A -MIM is any function that only depends on a -dimensional subsp…
Entangled Mean Estimation in High-Dimensions
Ilias Diakonikolas, Daniel M. Kane, Sihan Liu +1
We study the task of high-dimensional entangled mean estimation in the subset-of-signals model. Specifically, given independent random points in …
Active Learning of General Halfspaces: Label Queries vs Membership Queries
Ilias Diakonikolas, Daniel M. Kane, Mingchen Ma
We study the problem of learning general (i.e., not necessarily homogeneous) halfspaces under the Gaussian distribution on in the presence of some form of query access. In th…
Implicit High-Order Moment Tensor Estimation and Learning Latent Variable Models
Ilias Diakonikolas, Daniel M. Kane
We study the task of learning latent-variable models. A common algorithmic technique for this task is the method of moments. Unfortunately, moment-based approaches are hampered by…
Efficient Testable Learning of General Halfspaces with Adversarial Label Noise
Ilias Diakonikolas, Daniel M. Kane, Sihan Liu +1
We study the task of testable learning of general -- not necessarily homogeneous -- halfspaces with adversarial label noise with respect to the Gaussian distribution. In the testab…
Replicability in High Dimensional Statistics
Max Hopkins, Russell Impagliazzo, Daniel Kane +2
The replicability crisis is a major issue across nearly all areas of empirical science, calling for the formal study of replicability in statistics. Motivated in this context, [Imp…