activity
20152023
most citedDepth Separation for Neural Networks

17 citations · 61 across the 9 of their papers we have counts for

collaborators
Showing cs.LGShow all

22 papers · 1 filter

cs.LG2023

Multiclass Boosting: Simple and Intuitive Weak Learning Criteria

Nataly Brukhim, Amit Daniely, Yishay Mansour +1

We study a generalization of boosting to the multiclass setting. We introduce a weak learning condition for multiclass classification that captures the original notion of weak lear…

cs.LG2023

Most Neural Networks Are Almost Learnable

Amit Daniely, Nathan Srebro, Gal Vardi

We present a PTAS for learning random constant-depth networks. We show that for any fixed and depth , there is a poly-time algorithm that for any distribution on $\sqrt{d}…

cs.LG2022

Approximate Description Length, Covering Numbers, and VC Dimension

Amit Daniely, Gal Katzhendler

Recently, Daniely and Granot [arXiv:1910.05697] introduced a new notion of complexity called Approximate Description Length (ADL). They used it to derive novel generalization bound…

cs.LG2021

From Local Pseudorandom Generators to Hardness of Learning

Amit Daniely, Gal Vardi

We prove hardness-of-learning results under a well-studied assumption on the existence of local pseudorandom generators. As we show, this assumption allows us to surpass the curren…

cs.LG20203 cited

Most ReLU Networks Suffer from Adversarial Perturbations

Amit Daniely, Hadas Schacham

We consider ReLU networks with random weights, in which the dimension decreases at each layer. We show that for most such networks, most examples admit an adversarial perturbat…

cs.LG2020

Hardness of Learning Neural Networks with Natural Weights

Amit Daniely, Gal Vardi

Neural networks are nowadays highly successful despite strong hardness results. The existing hardness results focus on the network architecture, and assume that the network's weigh…