Corner Gradient Descent
This work addresses a bottleneck in optimization theory for machine learning practitioners, offering a novel method to improve SGD convergence in specific spectral conditions, though it is incremental relative to known deterministic results.
The paper tackles the problem of achieving optimal convergence rates in stochastic gradient descent (SGD) for infinite-dimensional quadratic problems with power law spectral conditions, showing that a generalized stationary SGD with infinite memory can achieve rates up to O(t^{-2ζ}), and it demonstrates practical efficiency on synthetic and MNIST datasets.
We consider SGD-type optimization on infinite-dimensional quadratic problems with power law spectral conditions. It is well-known that on such problems deterministic GD has loss convergence rates $L_t=O(t^{-ζ})$, which can be improved to $L_t=O(t^{-2ζ})$ by using Heavy Ball with a non-stationary Jacobi-based schedule (and the latter rate is optimal among fixed schedules). However, in the mini-batch Stochastic GD setting, the sampling noise causes the Jacobi HB to diverge; accordingly no $O(t^{-2ζ})$ algorithm is known. In this paper we show that rates up to $O(t^{-2ζ})$ can be achieved by a generalized stationary SGD with infinite memory. We start by identifying generalized (S)GD algorithms with contours in the complex plane. We then show that contours that have a corner with external angle $θπ$ accelerate the plain GD rate $O(t^{-ζ})$ to $O(t^{-θζ})$. For deterministic GD, increasing $θ$ allows to achieve rates arbitrarily close to $O(t^{-2ζ})$. However, in Stochastic GD, increasing $θ$ also amplifies the sampling noise, so in general $θ$ needs to be optimized by balancing the acceleration and noise effects. We prove that the optimal rate is given by $θ_{\max}=\min(2,ν,\tfrac{2}{ζ+1/ν})$, where $ν,ζ$ are the exponents appearing in the capacity and source spectral conditions. Furthermore, using fast rational approximations of the power functions, we show that ideal corner algorithms can be efficiently approximated by finite-memory algorithms, and demonstrate their practical efficiency on a synthetic problem and MNIST.