## Statistical and Computational Complexities of BFGS Quasi-Newton Method for Generalized Linear Models

**Abstract:**The gradient descent (GD) method has been used widely to solve parameter estimation in generalized linear models (GLMs), a generalization of linear models when the link function can be non-linear. In GLMs with a polynomial link function, it has been shown that in the high signal-to-noise ratio (SNR) regime, due to the problem's strong convexity and smoothness, GD converges linearly and reaches the final desired accuracy in a logarithmic number of iterations. In contrast, in the low SNR setting, where the problem becomes locally convex, GD converges at a slower rate and requires a polynomial number of iterations to reach the desired accuracy. Even though Newton's method can be used to resolve the flat curvature of the loss functions in the low SNR case, its computational cost is prohibitive in high-dimensional settings as it is $\mathcal{O}(d^3)$, where $d$ the is the problem dimension. To address the shortcomings of GD and Newton's method, we propose the use of the BFGS quasi-Newton method to solve parameter estimation of the GLMs, which has a per iteration cost of $\mathcal{O}(d^2)$. When the SNR is low, for GLMs with a polynomial link function of degree $p$, we demonstrate that the iterates of BFGS converge linearly to the optimal solution of the population least-square loss function, and the contraction coefficient of the BFGS algorithm is comparable to that of Newton's method. Moreover, the contraction factor of the linear rate is independent of problem parameters and only depends on the degree of the link function $p$. Also, for the empirical loss with $n$ samples, we prove that in the low SNR setting of GLMs with a polynomial link function of degree $p$, the iterates of BFGS reach a final statistical radius of $\mathcal{O}((d/n)^{\frac{1}{2p+2}})$ after at most $\log(n/d)$ iterations. This complexity is significantly less than the number required for GD, which scales polynomially with $(n/d)$.

**Submission Length:**Regular submission (no more than 12 pages of main content)

**Previous TMLR Submission Url:**https://openreview.net/forum?id=bL095uaGCU&referrer=%5BAuthor%20Console%5D(%2Fgroup%3Fid%3DTMLR%2FAuthors%23your-submissions)

**Changes Since Last Submission:**The previous submission doesn't follow TMLR's style file format (notably the font isn't the right one). So it was rejected. We have fixed the format, changed the font to the right size and resubmitted it here.

**Supplementary Material:**zip

**Assigned Action Editor:**~Sebastian_U_Stich1

**Submission Number:**1801

Loading