3 citations · 7 across the 7 of their papers we have counts for
9 papers
Oracle-Efficient Online Classification with Stochastic Inputs and Adversarial Outputs
Gon Buzaglo, Elad Hazan
We consider binary prediction with i.i.d. contexts from an unknown distribution and adaptively chosen losses. We show that a simple Follow-the-Perturbed-Leader algorithm using a Ga…
Convergence of Continual Learning in Homogeneous Deep Networks
Matan Schliserman, Gon Buzaglo, Itay Evron +1
We characterize weakly regularized continual classification in homogeneous models as sequential projections onto task margin sets. This result generalizes prior analyses restricted…
The Hidden Game Problem
Gon Buzaglo, Noah Golowich, Elad Hazan
This paper investigates a class of games with large strategy spaces, motivated by challenges in AI alignment and language games. We introduce the hidden game problem, where for eac…
Efficient Spectral Control of Partially Observed Linear Dynamical Systems
Anand Brahmbhatt, Gon Buzaglo, Sofiia Druchyna +1
We propose a new method for the problem of controlling linear dynamical systems under partial observation and adversarial disturbances. Our new algorithm, Double Spectral Control (…
A New Approach to Controlling Linear Dynamical Systems
Anand Brahmbhatt, Gon Buzaglo, Sofiia Druchyna +1
We propose a new method for controlling linear dynamical systems under adversarial disturbances and cost functions. Our algorithm achieves a running time that scales polylogarithmi…
How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teachers
Gon Buzaglo, Itamar Harel, Mor Shpigel Nacson +3
Background. A main theoretical puzzle is why over-parameterized Neural Networks (NNs) generalize well when trained to zero loss (i.e., so they interpolate the data). Usually, the N…
Deconstructing Data Reconstruction: Multiclass, Weight Decay and General Losses
Gon Buzaglo, Niv Haim, Gilad Yehudai +4
Memorization of training data is an active research area, yet our understanding of the inner workings of neural networks is still in its infancy. Recently, Haim et al. (2022) propo…
Continual Learning in Linear Classification on Separable Data
Itay Evron, Edward Moroshko, Gon Buzaglo +4
We analyze continual learning on a sequence of separable linear classification tasks with binary labels. We show theoretically that learning with weak regularization reduces to sol…
Reconstructing Training Data from Multiclass Neural Networks
Gon Buzaglo, Niv Haim, Gilad Yehudai +2
Reconstructing samples from the training set of trained neural networks is a major privacy concern. Haim et al. (2022) recently showed that it is possible to reconstruct training s…