21 citations · 35 across the 5 of their papers we have counts for
7 papers · 1 filter
Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy
Edward Moroshko, Suriya Gunasekar, Blake Woodworth +3
We provide a detailed asymptotic study of gradient flow trajectories and their implicit optimization bias when minimizing the exponential loss over "diagonal linear networks". This…
Kernel and Rich Regimes in Overparametrized Models
Blake Woodworth, Suriya Gunasekar, Jason D. Lee +5
A recent line of work studies overparametrized neural networks in the "kernel regime," i.e. when the network behaves during training as a kernelized linear predictor, and thus trai…
Kernel and Rich Regimes in Overparametrized Models
Blake Woodworth, Suriya Gunasekar, Pedro Savarese +5
A recent line of work studies overparametrized neural networks in the "kernel regime," i.e. when the network behaves during training as a kernelized linear predictor, and thus trai…
Multi Instance Learning For Unbalanced Data
Mark Kozdoba, Edward Moroshko, Lior Shani +4
In the context of Multi Instance Learning, we analyze the Single Instance (SI) learning objective. We show that when the data is unbalanced and the family of classifiers is suffici…
A Last-Step Regression Algorithm for Non-Stationary Online Learning
Edward Moroshko, Koby Crammer
The goal of a learner in standard online learning is to maintain an average loss close to the loss of the best-performing single function in some class. In many real-world problems…
Second-Order Non-Stationary Online Learning for Regression
Nina Vaits, Edward Moroshko, Koby Crammer
The goal of a learner, in standard online learning, is to have the cumulative loss not much larger compared with the best-performing function from some fixed class. Numerous algori…