3 citations · 3 across the 8 of their papers we have counts for
10 papers
Benign Overfitting for General Norms and Distributions
Daniel Barzilai, Ohad Shamir
Understanding why predictors can generalize despite interpolating noisy training data is a central puzzle in machine learning. Most work on such "benign overfitting" studies minimu…
When Is Compositional Reasoning Learnable from Verifiable Rewards?
Daniel Barzilai, Yotam Wolf, Ronen Basri
The emergence of compositional reasoning in large language models through reinforcement learning with verifiable rewards (RLVR) has been a key driver of recent empirical successes.…
Limitations of SGD for Multi-Index Models Beyond Statistical Queries
Daniel Barzilai, Ohad Shamir
Understanding the limitations of gradient methods, and stochastic gradient descent (SGD) in particular, is a central challenge in learning theory. To that end, a commonly used tool…
Querying Kernel Methods Suffices for Reconstructing their Training Data
Daniel Barzilai, Yuval Margalit, Eitan Gronich +3
Over-parameterized models have raised concerns about their potential to memorize training data, even when achieving strong generalization. The privacy implications of such memoriza…
When Models Don't Collapse: On the Consistency of Iterative MLE
Daniel Barzilai, Ohad Shamir
The widespread use of generative models has created a feedback loop, in which each generation of models is trained on data partially produced by its predecessors. This process has…
Beyond Benign Overfitting in Nadaraya-Watson Interpolators
Daniel Barzilai, Guy Kornowski, Ohad Shamir
In recent years, there has been much interest in understanding the generalization behavior of interpolating predictors, which overfit on noisy training data. Whereas standard analy…
Simple Relative Deviation Bounds for Covariance and Gram Matrices
Daniel Barzilai, Ohad Shamir
We provide non-asymptotic, relative deviation bounds for the eigenvalues of empirical covariance and Gram matrices in general settings. Unlike typical uniform bounds, which may fai…
Generalization in Kernel Regression Under Realistic Assumptions
Daniel Barzilai, Ohad Shamir
It is by now well-established that modern over-parameterized models seem to elude the bias-variance tradeoff and generalize well despite overfitting noise. Many recent works attemp…
Controlling the Inductive Bias of Wide Neural Networks by Modifying the Kernel's Spectrum
Amnon Geifman, Daniel Barzilai, Ronen Basri +1
Wide neural networks are biased towards learning certain functions, influencing both the rate of convergence of gradient descent (GD) and the functions that are reachable with GD i…
A Kernel Perspective of Skip Connections in Convolutional Networks
Daniel Barzilai, Amnon Geifman, Meirav Galun +1
Over-parameterized residual networks (ResNets) are amongst the most successful convolutional neural architectures for image processing. Here we study their properties through their…