Quantum Algorithms and Lower Bounds for Linear Regression with Norm Constraints
Lasso and Ridge are important minimization problems in machine learning and statistics. They are versions of linear regression with squared loss where the vector θ∈ℝ^d of coefficients is constrained in either ℓ_1-norm (for Lasso) or in ℓ_2-norm (for Ridge). We study the complexity of quantum algorithms for finding ε-minimizers for these minimization problems. We show that for Lasso we can get a quadratic quantum speedup in terms of d by speeding up the cost-per-iteration of the Frank-Wolfe algorithm, while for Ridge the best quantum algorithms are linear in d, as are the best classical algorithms.
READ FULL TEXT