Tight Bounds for Logistic Regression with Large Stepsize Gradient Descent in Low Dimension
We consider the optimization problem of minimizing the logistic loss with gradient descent to train a linear model for binary classification with separable data. With a budget of $T$ iterations, it was recently shown that an accelerated $1/T^2$ rate is possible by choosing a large stepsize $η= Θ(γ^2 T)$ (where $γ$ is the dataset's margin) despite the resulting non-monotonicity of the loss. In this paper, we provide a tighter analysis of gradient descent for this problem when the data is two-dimensional: we show that GD with a sufficiently large learning rate $η$ finds a point with loss smaller than $\mathcal{O}(1/(ηγ^2 T))$, as long as $T \geq Ω(n/γ+ 1/γ^2)$, where $n$ is the dataset size. Our improved rate comes from a tighter bound on the time $τ$ that it takes for GD to transition from unstable (non-monotonic loss) to stable (monotonic loss), via a fine-grained analysis of the oscillatory dynamics of GD in the subspace orthogonal to the max-margin classifier. We also provide a lower bound of $τ$ matching our upper bound up to logarithmic factors, showing that our analysis is tight.
Code (0)
등록된 구현이 없습니다.
Tasks
Binary ClassificationSimilar Papers 제목 키워드 기반
Feature Space Sketching for Logistic Regression
We present novel bounds for coreset construction, feature selection, and dimensionality reduction for logistic regression. All three approaches can be thought of as sketching the logistic regression inputs. On the corese…
Dimensionality Reductionfeature selectionregressionImplicit Bias of Gradient Descent for Logistic Regression at the Edge of Stability
Recent research has observed that in machine learning optimization, gradient descent (GD) often operates at the edge of stability (EoS) [Cohen, et al., 2021], where the stepsizes are set to be large, resulting in non-mon…
regressionConstant Stepsize Local GD for Logistic Regression: Acceleration by Instability
Existing analysis of Local (Stochastic) Gradient Descent for heterogeneous objectives requires stepsizes $\eta \leq 1/K$ where $K$ is the communication interval, which ensures monotonic decrease of the objective. In cont…
regressionLarge Stepsize Gradient Descent for Logistic Loss: Non-Monotonicity of the Loss Improves Optimization Efficiency
We consider gradient descent (GD) with a constant stepsize applied to logistic regression with linearly separable data, where the constant stepsize $\eta$ is so large that the loss initially oscillates. We show that GD e…
General ClassificationLast Iterate Risk Bounds of SGD with Decaying Stepsize for Overparameterized Linear Regression
Stochastic gradient descent (SGD) has been shown to generalize well in many deep learning applications. In practice, one often runs SGD with a geometrically decaying stepsize, i.e., a constant initial stepsize followed b…
regression