5 papers
Fast Last-Iterate Convergence of SGD in the Smooth Interpolation Regime
Amit Attia, Matan Schliserman, Uri Sherman +1
We study population convergence guarantees of stochastic gradient descent (SGD) for smooth convex objectives in the interpolation regime, where the noise at optimum is zero or near…
Optimal Rates in Continual Linear Regression via Increasing Regularization
Ran Levinstein, Amit Attia, Matan Schliserman +4
We study realizable continual linear regression under random task orderings, a common setting for developing continual learning theory. In this setup, the worst-case expected loss…
Multiclass Loss Geometry Matters for Generalization of Gradient Descent in Separable Classification
Matan Schliserman, Tomer Koren
We study the generalization performance of unregularized gradient methods for separable linear classification. While previous work mostly deal with the binary case, we focus on the…
From Continual Learning to SGD and Back: Better Rates for Continual Linear Models
Itay Evron, Ran Levinstein, Matan Schliserman +4
We study the common continual learning setup where an overparameterized model is sequentially fitted to a set of jointly realizable tasks. We analyze forgetting, defined as the los…
Complexity of Vector-valued Prediction: From Linear Models to Stochastic Convex Optimization
Matan Schliserman, Tomer Koren
We study the problem of learning vector-valued linear predictors: these are prediction rules parameterized by a matrix that maps an -dimensional feature vector to a -dimensio…