… In this paper, we develop a principled technique to give the first efficient list-decodable
learning algorithm for the fundamental problem of linear regression. Our algorithm takes a …

… We study the problem of list-decodable linear regression, … T are iid samples from a linear
regression model with Gaussian … them is close to the target regression vector. Our main result is …

… In the list-decodable linear regression problem, we are … for linear regression that are robust
to the presence of outliers. While there is an extensive literature on robust linear regression (…

… in the list-decodable setting were for the special cases of list-decodable linear regression
and … time exact algorithm for list-decodable linear regression and subspace recovery that, in …

… We demonstrate the use of batches in studying list-decodable linear regression, in which
only α ∈ (0, 1] fraction of batches contain genuine samples from a common distribution and the …

… mixtures of linear regressions and subspace clustering. On the other hand, the above
works also construct polynomial time, dpoly( 1 α ) , algorithms for regression and subspace …

… The model of computation used in this paper is the unit cost RAM. In this model, we allow the
… We now highlight how one can get list-decodable codes from list-recoverable codes using …

… ], is an error-recovery model where the decoder is allowed to … linear codes. Further, our
result in fact shows that a random Fq-linear code of rate 1 − Hq(p) − ε is (p, Cp,q/ε))-list-decodable …

… random linear binary rank-metric codes are more list-decodable … random linear binary
rankmetric codes are list-decodable to … Shannon model: with high probability, random linear codes …

… result imply that random linear codes of rate 1 − H(p) − ε are (p, L)-list-decodable with list-size
L … from the Shannon model: with high probability, random linear codes achieve capacity on …