We study on-line generalized linear regression with multidimensional outputs, i.e., neural networks with multiple output nodes but no hidden nodes. We allow at the final layer tra...
This work characterizes the generalization ability of algorithms whose predictions are linear in the input vector. To this end, we provide sharp bounds for Rademacher and Gaussian...
The estimation of a sparse vector in the linear model is a fundamental problem in signal processing, statistics, and compressive sensing. This paper establishes a lower bound on t...
We consider coGapSV P√ n, a gap version of the shortest vector in a lattice problem. This problem is known to be in AM ∩coNP but is not known to be in NP or in MA. We prove th...
We give a bound on the expected reconstruction error for a general coding method where data in a Hilbert space are represented by finite dimensional coding vectors. The result can...